mirror of
https://github.com/R0m1k3/Loki.git
synced 2026-10-17 04:10:04 +02:00
La façade sert la liste des presets (pastilles, mesures du bench quand elles correspondent à la configuration), leur ordre, l'éditeur (lecture, graine d'un preset neuf, enregistrement avec nom de fichier unique, prompt système), la suppression (refusée pour l'actif, modèle compris sur demande), les aperçus de l'éditeur (cache de prompts, second slot, avis MoE et de chargement, réutilisant le port de loki serve), la copie en placement auto, les presets externes (la clé n'est jamais rendue, test par un vrai appel de complétion) et la bascule, quand LOKI_PRESETS=rust (expérimental ; le Go reste le défaut). Ce qui touche au moteur reste au Go jusqu'à son lot : facade_presets.go expose /internal/v1/preset/apply (bascule avec état du slot gardé et moteur relancé ou arrêté, preset en service réappliqué) et /internal/v1/tune/guard (verrou de l'optimiseur), et remet les routes du tunnel à la façade. Parité : parity_presets_test.go tire du Go les fonctions pures et 70 appels de route avec presets/, models/ et la base après chacun, rejoués par tests/presets_api.rs ; bascule et application vérifiées de bout en bout contre le faux Go, presetApply côté Go. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016tcGfJWefW5kUGoC2wL8cv
2207 lines
69 KiB
JSON
2207 lines
69 KiB
JSON
{
|
|
"display_name": [
|
|
{
|
|
"content": "MODEL=a.gguf\n",
|
|
"name": "Alpha",
|
|
"out": "# NAME=Alpha\nMODEL=a.gguf\n"
|
|
},
|
|
{
|
|
"content": "# NAME=Vieux\nMODEL=a\n",
|
|
"name": "Neuf",
|
|
"out": "# NAME=Neuf\nMODEL=a\n"
|
|
},
|
|
{
|
|
"content": " name = x\nCTX=1\n",
|
|
"name": "Y",
|
|
"out": "# NAME=Y\nCTX=1\n"
|
|
},
|
|
{
|
|
"content": "#NAME=a\n# name=b\n",
|
|
"name": "Deux",
|
|
"out": "# NAME=Deux\n# NAME=Deux\n"
|
|
},
|
|
{
|
|
"content": "MODEL=a\n# NAME=x",
|
|
"name": "Prix $1 et ${x}",
|
|
"out": "MODEL=a\n# NAME=Prix et "
|
|
},
|
|
{
|
|
"content": "",
|
|
"name": "Vide",
|
|
"out": "# NAME=Vide\n"
|
|
}
|
|
],
|
|
"quote": {
|
|
"": "",
|
|
"\"y\"": "\"y\"",
|
|
"'x'": "\"'x'\"",
|
|
"'z": "'z",
|
|
"a\tb": "\"a\tb\"",
|
|
"a b": "\"a b\"",
|
|
"a\"b": "a\"b",
|
|
"simple": "simple"
|
|
},
|
|
"format_env": "A=\"deux mots\"\nM=\nQ=q\"q\nZ=1\n",
|
|
"names": {
|
|
"": "nom vide",
|
|
" ": "nom vide",
|
|
" pad ": "ok",
|
|
".": "nom réservé",
|
|
"..": "nom réservé",
|
|
"Qwen 3 (27B) é": "ok",
|
|
"a\u0000b": "le nom ne peut pas contenir / ni \\",
|
|
"a\u0001b": "le nom contient un caractère de contrôle invalide",
|
|
"a/b": "le nom ne peut pas contenir / ni \\",
|
|
"a\\b": "le nom ne peut pas contenir / ni \\"
|
|
},
|
|
"quant": {
|
|
"": "",
|
|
"# QUANT=iq3_xs\nMODEL=x-Q8_0.gguf\n": "IQ3_XS",
|
|
"MODEL = C:\\models\\w-BF16.gguf\n": "BF16",
|
|
"MODEL=\"/m/Llama-3-UD-Q6_K_XL-00001-of-00002.gguf\"\nREASONING=On\n": "Q6_K_XL",
|
|
"MODEL=Qwen3-27B-Q4_K_M.gguf\n": "Q4_K_M",
|
|
"QUANT='q5'\n": "Q5",
|
|
"export MODEL=z.gguf\n": "",
|
|
"reasoning = 'off'\n#REASONING=on\n": ""
|
|
},
|
|
"reasoning": {
|
|
"": "",
|
|
"# QUANT=iq3_xs\nMODEL=x-Q8_0.gguf\n": "",
|
|
"MODEL = C:\\models\\w-BF16.gguf\n": "",
|
|
"MODEL=\"/m/Llama-3-UD-Q6_K_XL-00001-of-00002.gguf\"\nREASONING=On\n": "On",
|
|
"MODEL=Qwen3-27B-Q4_K_M.gguf\n": "",
|
|
"QUANT='q5'\n": "",
|
|
"export MODEL=z.gguf\n": "",
|
|
"reasoning = 'off'\n#REASONING=on\n": "off"
|
|
},
|
|
"model": {
|
|
"": "",
|
|
"# QUANT=iq3_xs\nMODEL=x-Q8_0.gguf\n": "x-Q8_0.gguf",
|
|
"MODEL = C:\\models\\w-BF16.gguf\n": "C:\\models\\w-BF16.gguf",
|
|
"MODEL=\"/m/Llama-3-UD-Q6_K_XL-00001-of-00002.gguf\"\nREASONING=On\n": "/m/Llama-3-UD-Q6_K_XL-00001-of-00002.gguf",
|
|
"MODEL=Qwen3-27B-Q4_K_M.gguf\n": "Qwen3-27B-Q4_K_M.gguf",
|
|
"QUANT='q5'\n": "",
|
|
"export MODEL=z.gguf\n": "",
|
|
"reasoning = 'off'\n#REASONING=on\n": ""
|
|
},
|
|
"completions": {
|
|
"": "",
|
|
" https://api.groq.com/openai/v1/ ": "https://api.groq.com/openai/v1/chat/completions",
|
|
"http://loki:8090": "http://loki:8090/v1/chat/completions",
|
|
"http://x/chat/completions": "http://x/chat/completions",
|
|
"https://o.ai/api/v1": "https://o.ai/api/v1/chat/completions"
|
|
},
|
|
"external": [
|
|
{
|
|
"ctx": "",
|
|
"key": "",
|
|
"model": "gpt",
|
|
"out": "EXTERNAL=1\nEXTERNAL_MODEL=gpt\nEXTERNAL_URL=https://a/v1\n",
|
|
"url": "https://a/v1",
|
|
"vision": false
|
|
},
|
|
{
|
|
"ctx": " 128000 ",
|
|
"key": " k ",
|
|
"model": " m ",
|
|
"out": "CTX=128000\nEXTERNAL=1\nEXTERNAL_KEY=k\nEXTERNAL_MODEL=m\nEXTERNAL_URL=u\nEXTERNAL_VISION=1\n",
|
|
"url": " u ",
|
|
"vision": true
|
|
}
|
|
],
|
|
"api_error": {
|
|
"pas du json": "",
|
|
"{\"error\":\"x\"}": "",
|
|
"{\"error\":{\"message\":\" clé invalide \"}}": "clé invalide",
|
|
"{}": ""
|
|
},
|
|
"join": [
|
|
{
|
|
"args": [
|
|
"-ngl",
|
|
"30"
|
|
],
|
|
"out": "-ngl 30"
|
|
},
|
|
{
|
|
"args": [
|
|
"--chat-template-file",
|
|
"/a b/t.jinja"
|
|
],
|
|
"out": "--chat-template-file '/a b/t.jinja'"
|
|
},
|
|
{
|
|
"args": [
|
|
"x",
|
|
"l'apostrophe ici"
|
|
],
|
|
"out": "x \"l'apostrophe ici\""
|
|
},
|
|
{
|
|
"args": [
|
|
""
|
|
],
|
|
"out": "\"\""
|
|
}
|
|
],
|
|
"set_key": [
|
|
{
|
|
"content": "A=1\nB=2\n",
|
|
"key": "B",
|
|
"out": "A=1\nB=3\n",
|
|
"val": "3"
|
|
},
|
|
{
|
|
"content": "A=1\nexport B=2\nB=4\n",
|
|
"key": "B",
|
|
"out": "A=1\n",
|
|
"val": ""
|
|
},
|
|
{
|
|
"content": "A=1",
|
|
"key": "C",
|
|
"out": "A=1\nC=\"deux mots\"\n",
|
|
"val": "deux mots"
|
|
},
|
|
{
|
|
"content": "",
|
|
"key": "X",
|
|
"out": "X=1\n",
|
|
"val": "1"
|
|
},
|
|
{
|
|
"content": "NGL=999\n# NGL=1\n",
|
|
"key": "NGL",
|
|
"out": "# NGL=1\n",
|
|
"val": ""
|
|
},
|
|
{
|
|
"content": "K.E=1\nKXE=2\n",
|
|
"key": "K.E",
|
|
"out": "K.E=v\nKXE=2\n",
|
|
"val": "v"
|
|
}
|
|
],
|
|
"autoplace": [
|
|
{
|
|
"changes": null,
|
|
"err": "--fit resterait inactif (surcharge de tenseurs) : retire-le à la main d'abord",
|
|
"in": "# NAME=MoE\nMODEL=m.gguf\nCTX=65536\nNGL=999\nEXTRA_ARGS=-ot 'exps=CPU,per_layer_token_embd=CPU,blk\\.0=CUDA0' --n-cpu-moe 0 -ub 512 --mlock --fit off -ctk q8_0\n",
|
|
"out": ""
|
|
},
|
|
{
|
|
"changes": [
|
|
"retiré : --n-cpu-moe 30",
|
|
"retiré : -ts 1,1",
|
|
"UBATCH=2048, BATCH=4096 (avant : 512 / 2048)",
|
|
"--load-mode mmap",
|
|
"CTX conservé : 32768"
|
|
],
|
|
"err": "",
|
|
"in": "MODEL=m.gguf\nEXTRA_ARGS=--n-cpu-moe 30 -ts 1,1\n",
|
|
"out": "MODEL=m.gguf\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
{
|
|
"changes": null,
|
|
"err": "--fit resterait inactif (-sm row) : retire-le à la main d'abord",
|
|
"in": "MODEL=m.gguf\nEXTRA_ARGS=--cpu-moe -sm row\n",
|
|
"out": ""
|
|
},
|
|
{
|
|
"changes": null,
|
|
"err": "contexte « 0 » non chiffré : --fit pourrait le réduire pour tenir — donne un CTX chiffré d'abord",
|
|
"in": "MODEL=m.gguf\nEXTRA_ARGS=--cpu-moe\nCTX=0\n",
|
|
"out": ""
|
|
},
|
|
{
|
|
"changes": null,
|
|
"err": "SPLIT_MODE=tensor coupe --fit : retire-le d'abord",
|
|
"in": "MODEL=m.gguf\nEXTRA_ARGS=--cpu-moe\nSPLIT_MODE=tensor\n",
|
|
"out": ""
|
|
},
|
|
{
|
|
"changes": null,
|
|
"err": "rien à migrer : ce preset ne place pas d'experts à la main (-ot …exps…, --n-cpu-moe, --cpu-moe)",
|
|
"in": "MODEL=m.gguf\nEXTRA_ARGS=-ngl 40\n",
|
|
"out": ""
|
|
},
|
|
{
|
|
"changes": null,
|
|
"err": "preset externe : le modèle tourne ailleurs",
|
|
"in": "EXTERNAL=1\n",
|
|
"out": ""
|
|
},
|
|
{
|
|
"changes": [
|
|
"retiré : --cpu-moe",
|
|
"retiré : -b 1024",
|
|
"UBATCH=2048, BATCH=4096 (avant : 1024 / 2048)",
|
|
"--load-mode mmap",
|
|
"CTX conservé : 32768",
|
|
"cache KV conservé tel quel — garde-le identique pour comparer les deux presets"
|
|
],
|
|
"err": "",
|
|
"in": "MODEL=m\nEXTRA_ARGS=--cpu-moe --fit=on -b=1024\nKV_TYPE=q4_0\nUBATCH=1024\n",
|
|
"out": "MODEL=m\nEXTRA_ARGS=\"--fit on --load-mode mmap\"\nKV_TYPE=q4_0\nUBATCH=2048\nBATCH=4096\n"
|
|
}
|
|
],
|
|
"bench_fp": [
|
|
{
|
|
"cfg": {
|
|
"MODEL": "a.gguf"
|
|
},
|
|
"cur": {},
|
|
"out": "e3fbbb2b984dad580f7fc2c6085660e1013a2d4d"
|
|
},
|
|
{
|
|
"cfg": {
|
|
"CUDA_VISIBLE_DEVICES": "1",
|
|
"MODEL": "a.gguf"
|
|
},
|
|
"cur": {
|
|
"CUDA_VISIBLE_DEVICES": "0"
|
|
},
|
|
"out": "0c52a09078a6809ccde29379f7bf6e01c51a9a11"
|
|
},
|
|
{
|
|
"cfg": {
|
|
"MODEL": "a.gguf"
|
|
},
|
|
"cur": {
|
|
"CUDA_VISIBLE_DEVICES": " 0,1 "
|
|
},
|
|
"out": "63d3caa22a8aadb3db007d11f044263fcfacfcc5"
|
|
}
|
|
],
|
|
"imposes": {
|
|
"": false,
|
|
"/app/llama-server": true,
|
|
"/opt/custom/llama-server": true,
|
|
"{{HOME}}/backends/llama.cpp-prebuilt/llama-b2/llama-server": false,
|
|
"{{HOME}}/engine/b1/llama-server": false
|
|
},
|
|
"seed": {
|
|
"config/BIN": "/opt/custom/llama-server",
|
|
"config/HOST": "127.0.0.1",
|
|
"config/MODEL": "live.gguf",
|
|
"config/PORT": "8081"
|
|
},
|
|
"steps": [
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [],
|
|
"disk": {},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset",
|
|
"status": 200,
|
|
"out": {
|
|
"content": "BIN=/opt/custom/llama-server\nHOST=127.0.0.1\nPORT=8081\n",
|
|
"id": "",
|
|
"name": ""
|
|
},
|
|
"disk": {},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"name\":\"Qwen 27B\",\"content\":\"MODEL=Qwen3-27B-Q4_K_M.gguf\\nCTX=65536\\nREASONING=on\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Qwen 27B",
|
|
"name": "Qwen 27B",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"name\":\"Qwen 27B\",\"content\":\"MODEL=Qwen3-27B-Q8_0.gguf\\nMMPROJ=mm.gguf\\n\",\"sysprompt\":\" Réponds en français. \"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Qwen 27B (2)",
|
|
"name": "Qwen 27B",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q8_0.gguf\nMMPROJ=mm.gguf\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n"
|
|
},
|
|
"state": {
|
|
"sysprompt:Qwen 27B (2)": "Réponds en français."
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"name\":\"a/b\\\\c\",\"content\":\"MODEL=x.gguf\\nCTX=40000\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "a-b-c",
|
|
"name": "a/b\\c",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q8_0.gguf\nMMPROJ=mm.gguf\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"sysprompt:Qwen 27B (2)": "Réponds en français."
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"name\":\" \",\"content\":\"X=1\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "nom requis",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q8_0.gguf\nMMPROJ=mm.gguf\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"sysprompt:Qwen 27B (2)": "Réponds en français."
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"id\":\"../evil\",\"name\":\"E\",\"content\":\"X=1\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "le nom ne peut pas contenir / ni \\",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q8_0.gguf\nMMPROJ=mm.gguf\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"sysprompt:Qwen 27B (2)": "Réponds en français."
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"id\":\"Qwen 27B (2)\",\"name\":\"Qwen Q8\",\"content\":\"# NAME=ancien\\nMODEL=Qwen3-27B-Q8_0.gguf\\nQUANT=q8\\n\",\"sysprompt\":\"\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Qwen 27B (2)",
|
|
"name": "Qwen Q8",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "pas du json",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "invalid character 'p' looking for beginning of value",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"deleteModel\":\"oui\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "json: cannot unmarshal string into Go struct field presetSaveReq.deleteModel of type bool",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/save",
|
|
"body": "{\"name\":\"Strata\",\"content\":\"ENGINE=strata\\nSTRATA_VISION=0\\nCTX=1048576\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [
|
|
{
|
|
"active": false,
|
|
"ctx": "64K",
|
|
"id": "Qwen 27B",
|
|
"name": "Qwen 27B",
|
|
"quant": "Q4_K_M",
|
|
"reasoning": "on"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "32K",
|
|
"id": "Qwen 27B (2)",
|
|
"name": "Qwen Q8",
|
|
"quant": "Q8"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "1M",
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"strata": true
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "40K",
|
|
"id": "a-b-c",
|
|
"name": "a/b\\c"
|
|
}
|
|
],
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset?id=Qwen%2027B",
|
|
"status": 200,
|
|
"out": {
|
|
"content": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"id": "Qwen 27B",
|
|
"name": "Qwen 27B",
|
|
"sysprompt": ""
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset?id=Qwen%2027B%20(2)",
|
|
"status": 200,
|
|
"out": {
|
|
"content": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"id": "Qwen 27B (2)",
|
|
"name": "Qwen Q8",
|
|
"sysprompt": ""
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset?id=absent",
|
|
"status": 404,
|
|
"out": {
|
|
"error": "not found"
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset?id=../x",
|
|
"status": 404,
|
|
"out": {
|
|
"error": "not found"
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/presets/order",
|
|
"body": "{\"ids\":[\"Strata\",\"Qwen 27B (2)\"]}",
|
|
"status": 200,
|
|
"out": {
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"preset_order": [
|
|
"Strata",
|
|
"Qwen 27B (2)"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [
|
|
{
|
|
"active": false,
|
|
"ctx": "1M",
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"strata": true
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "32K",
|
|
"id": "Qwen 27B (2)",
|
|
"name": "Qwen Q8",
|
|
"quant": "Q8"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "64K",
|
|
"id": "Qwen 27B",
|
|
"name": "Qwen 27B",
|
|
"quant": "Q4_K_M",
|
|
"reasoning": "on"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "40K",
|
|
"id": "a-b-c",
|
|
"name": "a/b\\c"
|
|
}
|
|
],
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"preset_order": [
|
|
"Strata",
|
|
"Qwen 27B (2)"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/presets/order",
|
|
"body": "{}",
|
|
"status": 200,
|
|
"out": {
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"preset_order": null
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/presets/order",
|
|
"status": 405,
|
|
"out": {
|
|
"error": "POST attendu",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"preset_order": null
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/presets/order",
|
|
"body": "{\"ids\":\"x\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "json: cannot unmarshal string into Go struct field .ids of type []string",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"preset_order": null
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/presets/order",
|
|
"body": "{\"ids\":[\"a-b-c\"]}",
|
|
"status": 200,
|
|
"out": {
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"store": {
|
|
"state/bench_presets": "{\"Qwen 27B\":{\"result\":{\"prompt_per_second\":1234.5,\"predicted_per_second\":40,\"kv\":\"q8_0\",\"kv_quantized\":true,\"depth\":{\"cold\":{\"new\":30000},\"decode_per_second\":31.25}},\"model\":\"Qwen3-27B-Q4_K_M.gguf\",\"at\":1700000000},\"Qwen 27B (2)\":{\"result\":{\"prompt_per_second\":900,\"predicted_per_second\":20.5},\"model\":\"autre.gguf\",\"at\":1700000001},\"a-b-c\":{\"result\":{\"prompt_per_second\":1,\"predicted_per_second\":2},\"model\":\"x.gguf\",\"at\":1,\"fingerprint\":\"mauvaise\"}}"
|
|
},
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [
|
|
{
|
|
"active": false,
|
|
"ctx": "40K",
|
|
"id": "a-b-c",
|
|
"name": "a/b\\c"
|
|
},
|
|
{
|
|
"active": false,
|
|
"bench": {
|
|
"at": 1700000000,
|
|
"decode": 40,
|
|
"depth": 30000,
|
|
"depth_decode": 31.25,
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"prefill": 1234.5
|
|
},
|
|
"ctx": "64K",
|
|
"id": "Qwen 27B",
|
|
"name": "Qwen 27B",
|
|
"quant": "Q4_K_M",
|
|
"reasoning": "on"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "32K",
|
|
"id": "Qwen 27B (2)",
|
|
"name": "Qwen Q8",
|
|
"quant": "Q8"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "1M",
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"strata": true
|
|
}
|
|
],
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {
|
|
"Qwen 27B": {
|
|
"at": 1700000000,
|
|
"model": "Qwen3-27B-Q4_K_M.gguf",
|
|
"result": {
|
|
"depth": {
|
|
"cold": {
|
|
"new": 30000
|
|
},
|
|
"decode_per_second": 31.25
|
|
},
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"predicted_per_second": 40,
|
|
"prompt_per_second": 1234.5
|
|
}
|
|
},
|
|
"Qwen 27B (2)": {
|
|
"at": 1700000001,
|
|
"model": "autre.gguf",
|
|
"result": {
|
|
"predicted_per_second": 20.5,
|
|
"prompt_per_second": 900
|
|
}
|
|
},
|
|
"a-b-c": {
|
|
"at": 1,
|
|
"fingerprint": "mauvaise",
|
|
"model": "x.gguf",
|
|
"result": {
|
|
"predicted_per_second": 2,
|
|
"prompt_per_second": 1
|
|
}
|
|
}
|
|
},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"store": {
|
|
"config/BIN": "",
|
|
"config/CTX": "40000",
|
|
"config/HOST": "",
|
|
"config/MEM_MODE": "always",
|
|
"config/MODEL": "x.gguf",
|
|
"config/PORT": ""
|
|
},
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [
|
|
{
|
|
"active": true,
|
|
"ctx": "40K",
|
|
"id": "a-b-c",
|
|
"name": "a/b\\c"
|
|
},
|
|
{
|
|
"active": false,
|
|
"bench": {
|
|
"at": 1700000000,
|
|
"decode": 40,
|
|
"depth": 30000,
|
|
"depth_decode": 31.25,
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"prefill": 1234.5
|
|
},
|
|
"ctx": "64K",
|
|
"id": "Qwen 27B",
|
|
"name": "Qwen 27B",
|
|
"quant": "Q4_K_M",
|
|
"reasoning": "on"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "32K",
|
|
"id": "Qwen 27B (2)",
|
|
"name": "Qwen Q8",
|
|
"quant": "Q8"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "1M",
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"strata": true
|
|
}
|
|
],
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {
|
|
"Qwen 27B": {
|
|
"at": 1700000000,
|
|
"model": "Qwen3-27B-Q4_K_M.gguf",
|
|
"result": {
|
|
"depth": {
|
|
"cold": {
|
|
"new": 30000
|
|
},
|
|
"decode_per_second": 31.25
|
|
},
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"predicted_per_second": 40,
|
|
"prompt_per_second": 1234.5
|
|
}
|
|
},
|
|
"Qwen 27B (2)": {
|
|
"at": 1700000001,
|
|
"model": "autre.gguf",
|
|
"result": {
|
|
"predicted_per_second": 20.5,
|
|
"prompt_per_second": 900
|
|
}
|
|
},
|
|
"a-b-c": {
|
|
"at": 1,
|
|
"fingerprint": "mauvaise",
|
|
"model": "x.gguf",
|
|
"result": {
|
|
"predicted_per_second": 2,
|
|
"prompt_per_second": 1
|
|
}
|
|
}
|
|
},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":\"a-b-c\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "preset actif, switche d'abord",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/a-b-c.env": "# NAME=a/b\\c\nMODEL=x.gguf\nCTX=40000\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {
|
|
"Qwen 27B": {
|
|
"at": 1700000000,
|
|
"model": "Qwen3-27B-Q4_K_M.gguf",
|
|
"result": {
|
|
"depth": {
|
|
"cold": {
|
|
"new": 30000
|
|
},
|
|
"decode_per_second": 31.25
|
|
},
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"predicted_per_second": 40,
|
|
"prompt_per_second": 1234.5
|
|
}
|
|
},
|
|
"Qwen 27B (2)": {
|
|
"at": 1700000001,
|
|
"model": "autre.gguf",
|
|
"result": {
|
|
"predicted_per_second": 20.5,
|
|
"prompt_per_second": 900
|
|
}
|
|
},
|
|
"a-b-c": {
|
|
"at": 1,
|
|
"fingerprint": "mauvaise",
|
|
"model": "x.gguf",
|
|
"result": {
|
|
"predicted_per_second": 2,
|
|
"prompt_per_second": 1
|
|
}
|
|
}
|
|
},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"store": {
|
|
"config/MODEL": "autre.gguf"
|
|
},
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":\"a-b-c\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"freed": 0,
|
|
"modelDeleted": "",
|
|
"modelError": "",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {
|
|
"Qwen 27B": {
|
|
"at": 1700000000,
|
|
"model": "Qwen3-27B-Q4_K_M.gguf",
|
|
"result": {
|
|
"depth": {
|
|
"cold": {
|
|
"cached": 0,
|
|
"expected": 0,
|
|
"new": 30000,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 0,
|
|
"prompt_ms": 0,
|
|
"prompt_per_second": 0
|
|
},
|
|
"ctx": 0,
|
|
"decode_per_second": 31.25,
|
|
"reuse": 0,
|
|
"target": 0
|
|
},
|
|
"elapsed_sec": 0,
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 40,
|
|
"prompt_ms": 0,
|
|
"prompt_n": 0,
|
|
"prompt_per_second": 1234.5
|
|
}
|
|
},
|
|
"Qwen 27B (2)": {
|
|
"at": 1700000001,
|
|
"model": "autre.gguf",
|
|
"result": {
|
|
"elapsed_sec": 0,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 20.5,
|
|
"prompt_ms": 0,
|
|
"prompt_n": 0,
|
|
"prompt_per_second": 900
|
|
}
|
|
}
|
|
},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":\"absent\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "introuvable",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {
|
|
"Qwen 27B": {
|
|
"at": 1700000000,
|
|
"model": "Qwen3-27B-Q4_K_M.gguf",
|
|
"result": {
|
|
"depth": {
|
|
"cold": {
|
|
"cached": 0,
|
|
"expected": 0,
|
|
"new": 30000,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 0,
|
|
"prompt_ms": 0,
|
|
"prompt_per_second": 0
|
|
},
|
|
"ctx": 0,
|
|
"decode_per_second": 31.25,
|
|
"reuse": 0,
|
|
"target": 0
|
|
},
|
|
"elapsed_sec": 0,
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 40,
|
|
"prompt_ms": 0,
|
|
"prompt_n": 0,
|
|
"prompt_per_second": 1234.5
|
|
}
|
|
},
|
|
"Qwen 27B (2)": {
|
|
"at": 1700000001,
|
|
"model": "autre.gguf",
|
|
"result": {
|
|
"elapsed_sec": 0,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 20.5,
|
|
"prompt_ms": 0,
|
|
"prompt_n": 0,
|
|
"prompt_per_second": 900
|
|
}
|
|
}
|
|
},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":\"a/b\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "le nom ne peut pas contenir / ni \\",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Qwen 27B.env": "# NAME=Qwen 27B\nMODEL=Qwen3-27B-Q4_K_M.gguf\nCTX=65536\nREASONING=on\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {
|
|
"Qwen 27B": {
|
|
"at": 1700000000,
|
|
"model": "Qwen3-27B-Q4_K_M.gguf",
|
|
"result": {
|
|
"depth": {
|
|
"cold": {
|
|
"cached": 0,
|
|
"expected": 0,
|
|
"new": 30000,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 0,
|
|
"prompt_ms": 0,
|
|
"prompt_per_second": 0
|
|
},
|
|
"ctx": 0,
|
|
"decode_per_second": 31.25,
|
|
"reuse": 0,
|
|
"target": 0
|
|
},
|
|
"elapsed_sec": 0,
|
|
"kv": "q8_0",
|
|
"kv_quantized": true,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 40,
|
|
"prompt_ms": 0,
|
|
"prompt_n": 0,
|
|
"prompt_per_second": 1234.5
|
|
}
|
|
},
|
|
"Qwen 27B (2)": {
|
|
"at": 1700000001,
|
|
"model": "autre.gguf",
|
|
"result": {
|
|
"elapsed_sec": 0,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 20.5,
|
|
"prompt_ms": 0,
|
|
"prompt_n": 0,
|
|
"prompt_per_second": 900
|
|
}
|
|
}
|
|
},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"files": {
|
|
"models/Qwen3-27B-Q4_K_M.gguf": "poids"
|
|
},
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":\"Qwen 27B\",\"deleteModel\":true}",
|
|
"status": 200,
|
|
"out": {
|
|
"freed": 5,
|
|
"modelDeleted": "Qwen3-27B-Q4_K_M.gguf",
|
|
"modelError": "",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Qwen 27B (2).env": "# NAME=Qwen Q8\nMODEL=Qwen3-27B-Q8_0.gguf\nQUANT=q8\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {
|
|
"Qwen 27B (2)": {
|
|
"at": 1700000001,
|
|
"model": "autre.gguf",
|
|
"result": {
|
|
"elapsed_sec": 0,
|
|
"predicted_ms": 0,
|
|
"predicted_n": 0,
|
|
"predicted_per_second": 20.5,
|
|
"prompt_ms": 0,
|
|
"prompt_n": 0,
|
|
"prompt_per_second": 900
|
|
}
|
|
}
|
|
},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"files": {
|
|
"models/Qwen3-27B-Q8_0.gguf": "poids8",
|
|
"presets/Copie.env": "# NAME=Copie\nMODEL=Qwen3-27B-Q8_0.gguf\n"
|
|
},
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":\"Qwen 27B (2)\",\"deleteModel\":true}",
|
|
"status": 200,
|
|
"out": {
|
|
"freed": 6,
|
|
"modelDeleted": "Qwen3-27B-Q8_0.gguf",
|
|
"modelError": "supprimé, mais il était aussi référencé par : Copie",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Copie.env": "# NAME=Copie\nMODEL=Qwen3-27B-Q8_0.gguf\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":\"Copie\",\"deleteModel\":true}",
|
|
"status": 200,
|
|
"out": {
|
|
"freed": 0,
|
|
"modelDeleted": "",
|
|
"modelError": "modèle introuvable: Qwen3-27B-Q8_0.gguf",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/delete",
|
|
"body": "{\"id\":3}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "json: cannot unmarshal number into Go struct field presetSaveReq.id of type string",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [
|
|
{
|
|
"active": false,
|
|
"ctx": "1M",
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"strata": true
|
|
}
|
|
],
|
|
"disk": {
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset/external",
|
|
"status": 200,
|
|
"out": {
|
|
"hasKey": false,
|
|
"id": "",
|
|
"model": "",
|
|
"name": "",
|
|
"url": ""
|
|
},
|
|
"disk": {
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/save",
|
|
"body": "{\"name\":\" Groq \",\"url\":\" https://api.groq.com/openai/v1 \",\"model\":\" llama \",\"key\":\"k1\",\"ctx\":\"131072\",\"vision\":true}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Groq",
|
|
"name": "Groq",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nCTX=131072\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=llama\nEXTERNAL_URL=https://api.groq.com/openai/v1\nEXTERNAL_VISION=1\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/save",
|
|
"body": "{\"name\":\"X\",\"url\":\"\",\"model\":\"m\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "URL requise",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nCTX=131072\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=llama\nEXTERNAL_URL=https://api.groq.com/openai/v1\nEXTERNAL_VISION=1\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/save",
|
|
"body": "{\"name\":\"X\",\"url\":\"u\",\"model\":\" \"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "modèle requis",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nCTX=131072\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=llama\nEXTERNAL_URL=https://api.groq.com/openai/v1\nEXTERNAL_VISION=1\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/save",
|
|
"body": "{\"name\":\"\",\"url\":\"u\",\"model\":\"m\"}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "nom requis",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nCTX=131072\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=llama\nEXTERNAL_URL=https://api.groq.com/openai/v1\nEXTERNAL_VISION=1\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset/external?id=Groq",
|
|
"status": 200,
|
|
"out": {
|
|
"ctx": "131072",
|
|
"hasKey": true,
|
|
"id": "Groq",
|
|
"model": "llama",
|
|
"name": "Groq",
|
|
"url": "https://api.groq.com/openai/v1",
|
|
"vision": true
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nCTX=131072\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=llama\nEXTERNAL_URL=https://api.groq.com/openai/v1\nEXTERNAL_VISION=1\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/save",
|
|
"body": "{\"id\":\"Groq\",\"name\":\"Groq 2\",\"url\":\"https://api.groq.com\",\"model\":\"llama-3\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Groq",
|
|
"name": "Groq 2",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq 2\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset/external?id=Groq",
|
|
"status": 200,
|
|
"out": {
|
|
"ctx": "",
|
|
"hasKey": true,
|
|
"id": "Groq",
|
|
"model": "llama-3",
|
|
"name": "Groq 2",
|
|
"url": "https://api.groq.com",
|
|
"vision": false
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq 2\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/save",
|
|
"body": "{\"id\":\"Groq\",\"name\":\"Groq\",\"url\":\"https://api.groq.com\",\"model\":\"llama-3\",\"keyTouched\":true,\"key\":\"\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Groq",
|
|
"name": "Groq",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset/external?id=Groq",
|
|
"status": 200,
|
|
"out": {
|
|
"ctx": "",
|
|
"hasKey": false,
|
|
"id": "Groq",
|
|
"model": "llama-3",
|
|
"name": "Groq",
|
|
"url": "https://api.groq.com",
|
|
"vision": false
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset/external?id=Strata",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "pas un preset externe"
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset/external?id=absent",
|
|
"status": 404,
|
|
"out": {
|
|
"error": "not found"
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [
|
|
{
|
|
"active": false,
|
|
"external": true,
|
|
"id": "Groq",
|
|
"model": "llama-3",
|
|
"name": "Groq"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "1M",
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"strata": true
|
|
}
|
|
],
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/test",
|
|
"body": "{\"url\":\"{{URL}}/ok\",\"model\":\"m\",\"key\":\"k1\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/test",
|
|
"body": "{\"url\":\"{{URL}}/refus/v1\",\"model\":\"m\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"error": "clé invalide",
|
|
"ok": false,
|
|
"status": 401
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/test",
|
|
"body": "{\"url\":\"{{URL}}/brut/v1/chat/completions\",\"model\":\"m\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"error": "page absente",
|
|
"ok": false,
|
|
"status": 404
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/test",
|
|
"body": "{\"url\":\"{{URL}}/rien\",\"model\":\"m\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"error": "500 Internal Server Error",
|
|
"ok": false,
|
|
"status": 500
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/test",
|
|
"body": "{\"url\":\"\",\"model\":\"m\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"error": "URL et modèle requis",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/save",
|
|
"body": "{\"name\":\"Clé\",\"url\":\"{{URL}}/ok\",\"model\":\"m\",\"key\":\"k1\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"applied": false,
|
|
"id": "Clé",
|
|
"name": "Clé",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/test",
|
|
"body": "{\"id\":\"Clé\",\"url\":\"{{URL}}/ok\",\"model\":\"m\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/external/test",
|
|
"body": "[]",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "json: cannot unmarshal array into Go value of type loki.externalSaveReq",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/preset/autoplace",
|
|
"status": 405,
|
|
"out": {
|
|
"error": "méthode GET refusée : POST attendu",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/autoplace",
|
|
"body": "{\"id\":\"MoE\",\"content\":\"# NAME=MoE\\nMODEL=absent.gguf\\nCTX=32768\\nEXTRA_ARGS=--n-cpu-moe 20 --load-mode none\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"changes": [
|
|
"retiré : --n-cpu-moe 20",
|
|
"retiré : --load-mode none",
|
|
"UBATCH=2048, BATCH=4096 (avant : 512 / 2048)",
|
|
"--load-mode mmap",
|
|
"CTX conservé : 32768"
|
|
],
|
|
"id": "MoE (placement auto)",
|
|
"name": "MoE (placement auto)",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/autoplace",
|
|
"body": "{\"name\":\" Mon MoE \",\"content\":\"MODEL=m\\nEXTRA_ARGS=-ngl 30\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"error": "rien à migrer : ce preset ne place pas d'experts à la main (-ot …exps…, --n-cpu-moe, --cpu-moe)",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/autoplace",
|
|
"body": "{\"content\":\"MODEL=m\\nEXTRA_ARGS=--cpu-moe\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"changes": [
|
|
"retiré : --cpu-moe",
|
|
"UBATCH=2048, BATCH=4096 (avant : 512 / 2048)",
|
|
"--load-mode mmap",
|
|
"CTX conservé : 32768"
|
|
],
|
|
"id": "preset (placement auto)",
|
|
"name": "preset (placement auto)",
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/moe",
|
|
"body": "{\"content\":\"# NAME=MoE\\nMODEL=absent.gguf\\nCTX=32768\\nEXTRA_ARGS=--n-cpu-moe 20 --load-mode none\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"autoplace": {
|
|
"changes": [
|
|
"retiré : --n-cpu-moe 20",
|
|
"retiré : --load-mode none",
|
|
"UBATCH=2048, BATCH=4096 (avant : 512 / 2048)",
|
|
"--load-mode mmap",
|
|
"CTX conservé : 32768"
|
|
],
|
|
"ok": true
|
|
},
|
|
"load": "",
|
|
"notes": null,
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/moe",
|
|
"body": "{\"content\":\"EXTERNAL=1\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"load": "",
|
|
"notes": null,
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/moe",
|
|
"body": "{\"content\":\"MODEL=absent.gguf\\nEXTRA_ARGS=--cpu-moe -sm row\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"autoplace": {
|
|
"ok": false,
|
|
"why": "--fit resterait inactif (-sm row) : retire-le à la main d'abord"
|
|
},
|
|
"load": "",
|
|
"notes": null,
|
|
"ok": true
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/moe",
|
|
"body": "{\"content\":5}",
|
|
"status": 400,
|
|
"out": {
|
|
"error": "json: cannot unmarshal number into Go struct field .content of type string",
|
|
"ok": false
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/cacheram",
|
|
"body": "{\"content\":\"EXTERNAL=1\\nSIDE_SLOT=on\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"default": 8192,
|
|
"mib": 0,
|
|
"ok": true,
|
|
"side": {
|
|
"on": false,
|
|
"vramMiB": 0,
|
|
"why": "preset externe"
|
|
},
|
|
"why": "preset externe"
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/cacheram",
|
|
"body": "{\"content\":\"EXTRA_ARGS=-cram 2048\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"default": 8192,
|
|
"mib": 2048,
|
|
"ok": true,
|
|
"why": "fixé par EXTRA_ARGS"
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/cacheram",
|
|
"body": "{\"content\":\"CACHE_RAM=4096\\nSIDE_SLOT=on\\nMODEL=absent.gguf\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"default": 8192,
|
|
"mib": 4096,
|
|
"ok": true,
|
|
"side": {
|
|
"on": false,
|
|
"vramMiB": 0,
|
|
"why": "VRAM NVIDIA inconnue (macOS, AMD, --device…)"
|
|
},
|
|
"why": "fixé par CACHE_RAM"
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/cacheram",
|
|
"body": "{\"content\":\"CACHE_RAM=beaucoup\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"default": 8192,
|
|
"mib": 0,
|
|
"ok": true,
|
|
"why": "CACHE_RAM illisible"
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/cacheram",
|
|
"body": "{\"content\":\"CACHE_RAM=auto\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"default": 8192,
|
|
"mib": 0,
|
|
"ok": true,
|
|
"why": "modèle introuvable"
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/cacheram",
|
|
"body": "{\"content\":\"MODEL=absent.gguf\\nSIDE_SLOT=on\\nPARALLEL=3\\n\"}",
|
|
"status": 200,
|
|
"out": {
|
|
"default": 8192,
|
|
"mib": 0,
|
|
"ok": true,
|
|
"side": {
|
|
"on": false,
|
|
"vramMiB": 0,
|
|
"why": "PARALLEL=3 (SIDE_SLOT ouvre exactement 2 slots)"
|
|
},
|
|
"why": "VRAM NVIDIA inconnue"
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "POST",
|
|
"path": "/api/preset/cacheram",
|
|
"body": "{}",
|
|
"status": 200,
|
|
"out": {
|
|
"default": 8192,
|
|
"mib": 0,
|
|
"ok": true,
|
|
"why": "modèle introuvable"
|
|
},
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"method": "GET",
|
|
"path": "/api/presets",
|
|
"status": 200,
|
|
"out": [
|
|
{
|
|
"active": false,
|
|
"external": true,
|
|
"id": "Clé",
|
|
"model": "m",
|
|
"name": "Clé"
|
|
},
|
|
{
|
|
"active": false,
|
|
"external": true,
|
|
"id": "Groq",
|
|
"model": "llama-3",
|
|
"name": "Groq"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "32K",
|
|
"id": "MoE (placement auto)",
|
|
"name": "MoE (placement auto)"
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "1M",
|
|
"id": "Strata",
|
|
"name": "Strata",
|
|
"strata": true
|
|
},
|
|
{
|
|
"active": false,
|
|
"ctx": "32K",
|
|
"id": "preset (placement auto)",
|
|
"name": "preset (placement auto)"
|
|
}
|
|
],
|
|
"disk": {
|
|
"presets/Clé.env": "# NAME=Clé\nEXTERNAL=1\nEXTERNAL_KEY=k1\nEXTERNAL_MODEL=m\nEXTERNAL_URL={{URL}}/ok\n",
|
|
"presets/Groq.env": "# NAME=Groq\nEXTERNAL=1\nEXTERNAL_MODEL=llama-3\nEXTERNAL_URL=https://api.groq.com\n",
|
|
"presets/MoE (placement auto).env": "# NAME=MoE (placement auto)\nMODEL=absent.gguf\nCTX=32768\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n",
|
|
"presets/Strata.env": "# NAME=Strata\nENGINE=strata\nSTRATA_VISION=0\nCTX=1048576\n",
|
|
"presets/preset (placement auto).env": "# NAME=preset (placement auto)\nMODEL=m\nEXTRA_ARGS=\"--load-mode mmap\"\nUBATCH=2048\nBATCH=4096\n"
|
|
},
|
|
"state": {
|
|
"bench_presets": {},
|
|
"preset_order": [
|
|
"a-b-c"
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|