mirror of
https://github.com/R0m1k3/Loki.git
synced 2026-10-16 19:59:56 +02:00
Lot 28 : optimiseur tenu par la façade (LOKI_TUNE=rust)
Avec LOKI_TUNE=rust (expérimental, Unix seulement), la façade sert /api/tune, /api/tune/status, /api/tune/cancel, /api/tune/apply et /api/tune/last, et déroule l'optimisation sans perte (rust/loki-rs/src/tune) : vrai moteur arrêté, essais composés à blanc puis lancés par les « loki serve » du Go (LOKI_TUNE_TRIAL), chacun dans son groupe de processus, mesurés par le bench complet à profondeur fixe, retenus au-delà du bruit ; vrai moteur relancé. Rien n'est écrit sans un clic : copie du preset, ou le preset lui-même — redémarrage, sonde, et ancienne version rétablie si elle échoue. - tune/core.rs : la partie pure (EXTRA_ARGS, réglages, essais de chaque étape, garde-fous, diff et réécriture du preset, score) ; - tune/lock.rs : le verrou tune.lock au format du Go, identité des processus comme procIdentity (la reprise du Go reconnaît la façade vivante, et écarte son verrou si elle meurt), ménage d'un verrou périmé (essai orphelin arrêté, application interrompue défaite) ; - tune/job.rs : routes, job, essais et application. Le verrou de génération reste celui du Go, pris par le bail du moteur au motif « tune » (refus de l'optimiseur pour les autres, stop du chat qui annule). Le Go prête /internal/v1/tune/context (bench, génération, jobs du mode code, état du moteur, télémétrie) et le démarrage ou l'arrêt du moteur sans le refus de l'optimiseur (service/action « os »). Hors Unix, la façade passe LOKI_TUNE vide au Go, qui garde l'optimiseur. serde_json lit désormais les flottants à l'arrondi exact (float_roundtrip), comme le Go. Parité : parity_tune_test.go tire du Go un journal (partie pure, contenu du verrou, résultat enregistré, vérification après application) rejoué par tests/tune_core.rs. tests/tune.rs déroule de vraies optimisations, le binaire de test jouant « loki serve » ; les tests du verrou du Go sont portés ; TestFacadeTune côté Go. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016tcGfJWefW5kUGoC2wL8cv
This commit is contained in:
31 files changed
+36838
-25
No files matched your search
@@ -109,7 +109,7 @@ func TestFacadeBench(t *testing.T) {
|
||||
conv.extLeaseClearLocked()
|
||||
conv.Generating = false
|
||||
conv.mu.Unlock()
|
||||
if _, err := conv.extLeaseAcquire(5*time.Second, true); err != nil {
|
||||
if _, err := conv.extLeaseAcquire(5*time.Second, errBenchBusy); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
conv.mu.Lock()
|
||||
|
||||
@@ -183,6 +183,8 @@ func withFacadeChat(path string, h http.HandlerFunc) http.HandlerFunc {
|
||||
held, unavailable = facadeTasks, "tâches indisponibles : "
|
||||
case facadeBenchRoutes[path]:
|
||||
held, unavailable = facadeBench, "banc d'essai indisponible : "
|
||||
case facadeTuneRoutes[path]:
|
||||
held, unavailable = facadeTune, "optimiseur indisponible : "
|
||||
default:
|
||||
return h
|
||||
}
|
||||
|
||||
@@ -64,6 +64,9 @@ func handleInternalCDPShutdown(w http.ResponseWriter, r *http.Request) {
|
||||
// internalServiceAction : serviceAction, variable pour les tests.
|
||||
var internalServiceAction = serviceAction
|
||||
|
||||
// internalServiceActionOS : serviceActionOS, variable pour les tests.
|
||||
var internalServiceActionOS = func(a string) error { return serviceActionOSFn(a) }
|
||||
|
||||
// handleInternalServiceAction : POST {action, if_active} → 200 {ran, error}.
|
||||
// if_active : seulement si le moteur tourne (une clé neuve ne s'applique qu'au
|
||||
// redémarrage, inutile de démarrer un moteur arrêté pour elle).
|
||||
@@ -75,6 +78,9 @@ func handleInternalServiceAction(w http.ResponseWriter, r *http.Request) {
|
||||
var in struct {
|
||||
Action string `json:"action"`
|
||||
IfActive bool `json:"if_active"`
|
||||
// OS : sans le refus de l'optimiseur (serviceActionOS) — pour la
|
||||
// façade qui tient elle-même son verrou (LOKI_TUNE=rust).
|
||||
OS bool `json:"os"`
|
||||
}
|
||||
if err := json.NewDecoder(r.Body).Decode(&in); err != nil {
|
||||
sendJSON(w, http.StatusBadRequest, map[string]any{"error": err.Error()})
|
||||
@@ -90,9 +96,16 @@ func handleInternalServiceAction(w http.ResponseWriter, r *http.Request) {
|
||||
sendJSON(w, http.StatusOK, map[string]any{"ran": false, "error": ""})
|
||||
return
|
||||
}
|
||||
act := internalServiceAction
|
||||
if in.OS {
|
||||
act = internalServiceActionOS
|
||||
}
|
||||
msg := ""
|
||||
if err := internalServiceAction(in.Action); err != nil {
|
||||
if err := act(in.Action); err != nil {
|
||||
msg = err.Error()
|
||||
}
|
||||
if in.OS {
|
||||
gpuMonitor.invalidate()
|
||||
}
|
||||
sendJSON(w, http.StatusOK, map[string]any{"ran": true, "error": msg})
|
||||
}
|
||||
@@ -0,0 +1,70 @@
|
||||
package loki
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net/http"
|
||||
"os"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// facade_tune.go — l'optimiseur tenu par la façade Rust (LOKI_TUNE=rust, lot
|
||||
// 28 de la migration ; expérimental, le Go reste le défaut) : les routes
|
||||
// /api/tune*, le job, les essais et l'application (rust/loki-rs/src/tune).
|
||||
//
|
||||
// Le verrou de l'optimiseur reste le FICHIER de LOKI_HOME, au même format
|
||||
// (backend_tune_lock.go) : le Go le lit (tuneGuard), et sa reprise
|
||||
// (tuneRecoverWatch) écarte celui d'une façade morte — essai orphelin arrêté,
|
||||
// application défaite, moteur relancé. Le verrou de génération : le bail du
|
||||
// moteur, motif « tune » (errTuneBusy pour les autres, le stop du chat
|
||||
// annule). Les essais restent des « loki serve » du Go (LOKI_TUNE_TRIAL).
|
||||
//
|
||||
// Le Go prête ce qu'il est seul à voir (handleInternalTuneContext) et le
|
||||
// démarrage et l'arrêt du moteur SANS le refus de l'optimiseur
|
||||
// (handleInternalServiceAction, « os ») : c'est la façade qui tient le verrou.
|
||||
|
||||
const facadeTuneEnv = "LOKI_TUNE"
|
||||
|
||||
// facadeTune : la façade tient-elle l'optimiseur ?
|
||||
func facadeTune() bool {
|
||||
return strings.EqualFold(strings.TrimSpace(os.Getenv(facadeTuneEnv)), "rust") &&
|
||||
facadeAddr() != "" && internalToken() != ""
|
||||
}
|
||||
|
||||
// facadeTuneRoutes : les routes que la façade sert alors.
|
||||
var facadeTuneRoutes = map[string]bool{
|
||||
"/api/tune": true,
|
||||
"/api/tune/status": true,
|
||||
"/api/tune/cancel": true,
|
||||
"/api/tune/apply": true,
|
||||
"/api/tune/last": true,
|
||||
}
|
||||
|
||||
// handleInternalTuneContext : GET → {busy, main_active, perf}.
|
||||
//
|
||||
// - busy : ce qui interdit d'optimiser dans le processus web
|
||||
// (tunePreflight) — un benchmark, une génération, des jobs du mode code ;
|
||||
// "" sinon ;
|
||||
// - main_active : le vrai moteur tourne (engineNeedsStop) ;
|
||||
// - perf : la télémétrie, d'où l'optimiseur tire les poids d'un tour type.
|
||||
func handleInternalTuneContext(w http.ResponseWriter, r *http.Request) {
|
||||
if r.Method != http.MethodGet {
|
||||
w.Header().Set("Allow", http.MethodGet)
|
||||
sendJSON(w, http.StatusMethodNotAllowed, map[string]any{"error": "GET attendu"})
|
||||
return
|
||||
}
|
||||
busy := ""
|
||||
switch {
|
||||
case benchRunning():
|
||||
busy = errBenchBusy.Error()
|
||||
case conv.isGenerating():
|
||||
busy = "génération en cours"
|
||||
if err := conv.busyReason(); err != nil {
|
||||
busy = err.Error()
|
||||
}
|
||||
case bgJobsRunning() > 0:
|
||||
busy = fmt.Sprintf("%d job(s) d'arrière-plan du mode code tournent encore (bash_bg) : ils fausseraient les mesures — arrête-les d'abord",
|
||||
bgJobsRunning())
|
||||
}
|
||||
sendJSON(w, http.StatusOK, map[string]any{"busy": busy, "main_active": engineNeedsStop(),
|
||||
"perf": perfLog.snapshot()})
|
||||
}
|
||||
@@ -0,0 +1,168 @@
|
||||
package loki
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// L'optimiseur part à la façade avec LOKI_TUNE=rust (lot 28) ; le reste,
|
||||
// non. La façade tient le verrou de génération par le bail du moteur, motif
|
||||
// « tune » ; le Go lui prête ce qu'il est seul à voir et le démarrage du
|
||||
// moteur sans le refus de l'optimiseur.
|
||||
func TestFacadeTune(t *testing.T) {
|
||||
testHome(t)
|
||||
var mu sync.Mutex
|
||||
var calls []string
|
||||
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.Header.Get(internalTokenHeader) != jetonTest {
|
||||
w.WriteHeader(403)
|
||||
return
|
||||
}
|
||||
mu.Lock()
|
||||
calls = append(calls, r.Method+" "+r.URL.Path)
|
||||
mu.Unlock()
|
||||
io.WriteString(w, `{"ok":true,"de":"facade"}`)
|
||||
}))
|
||||
defer srv.Close()
|
||||
t.Setenv(internalTokenEnv, jetonTest)
|
||||
t.Setenv(facadeAddrEnv, strings.TrimPrefix(srv.URL, "http://"))
|
||||
local := func(w http.ResponseWriter, r *http.Request) { io.WriteString(w, "go") }
|
||||
|
||||
t.Setenv(facadeTuneEnv, "")
|
||||
if facadeTune() {
|
||||
t.Fatal("tenu sans LOKI_TUNE")
|
||||
}
|
||||
for p := range facadeTuneRoutes {
|
||||
w := httptest.NewRecorder()
|
||||
withFacadeChat(p, local)(w, httptest.NewRequest("POST", p, strings.NewReader("{}")))
|
||||
if w.Body.String() != "go" {
|
||||
t.Fatalf("sans LOKI_TUNE, %s : %q", p, w.Body.String())
|
||||
}
|
||||
}
|
||||
t.Setenv(facadeTuneEnv, " RUST")
|
||||
if len(facadeTuneRoutes) != 5 {
|
||||
t.Fatalf("routes : %v", facadeTuneRoutes)
|
||||
}
|
||||
for p := range facadeTuneRoutes {
|
||||
w := httptest.NewRecorder()
|
||||
withFacadeChat(p, local)(w, httptest.NewRequest("POST", p, strings.NewReader("{}")))
|
||||
if !strings.Contains(w.Body.String(), "facade") {
|
||||
t.Fatalf("%s non relayé : %q", p, w.Body.String())
|
||||
}
|
||||
}
|
||||
mu.Lock()
|
||||
n := len(calls)
|
||||
mu.Unlock()
|
||||
if n != len(facadeTuneRoutes) {
|
||||
t.Fatalf("relais : %v", calls)
|
||||
}
|
||||
w := httptest.NewRecorder()
|
||||
withFacadeChat("/api/bench", local)(w, httptest.NewRequest("POST", "/api/bench", nil))
|
||||
if w.Body.String() != "go" {
|
||||
t.Fatalf("le banc d'essai reste au Go : %q", w.Body.String())
|
||||
}
|
||||
|
||||
post := func(h http.HandlerFunc, path, body string) (int, map[string]any) {
|
||||
rec := httptest.NewRecorder()
|
||||
h(rec, httptest.NewRequest("POST", path, strings.NewReader(body)))
|
||||
var out map[string]any
|
||||
_ = json.Unmarshal(rec.Body.Bytes(), &out)
|
||||
return rec.Code, out
|
||||
}
|
||||
tuneCtx := func() map[string]any {
|
||||
rec := httptest.NewRecorder()
|
||||
handleInternalTuneContext(rec, httptest.NewRequest("GET", "/internal/v1/tune/context", nil))
|
||||
if rec.Code != 200 {
|
||||
t.Fatalf("contexte : %d", rec.Code)
|
||||
}
|
||||
var out map[string]any
|
||||
if err := json.Unmarshal(rec.Body.Bytes(), &out); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// Au repos : rien n'interdit, la télémétrie suit.
|
||||
perfRecord(perfRec{Kind: perfMain, Complete: true, Total: 100, New: 100, Gen: 10}, nil)
|
||||
c := tuneCtx()
|
||||
if c["busy"] != "" || c["main_active"] != false {
|
||||
t.Fatalf("contexte au repos : %v", c)
|
||||
}
|
||||
if perf, _ := c["perf"].([]any); len(perf) == 0 {
|
||||
t.Fatalf("télémétrie absente : %v", c["perf"])
|
||||
}
|
||||
rec := httptest.NewRecorder()
|
||||
handleInternalTuneContext(rec, httptest.NewRequest("POST", "/internal/v1/tune/context", nil))
|
||||
if rec.Code != 405 || rec.Header().Get("Allow") != "GET" {
|
||||
t.Fatalf("POST : %d", rec.Code)
|
||||
}
|
||||
|
||||
// Le bail « tune » : les autres reçoivent le refus de l'optimiseur ; ce
|
||||
// n'est pas un benchmark.
|
||||
code, out := post(handleInternalLease, "/internal/v1/engine/lease", `{"ttl_ms":60000,"why":"tune"}`)
|
||||
if code != 200 {
|
||||
t.Fatalf("bail : %d %v", code, out)
|
||||
}
|
||||
id, _ := out["lease"].(string)
|
||||
if conv.busyReason() != errTuneBusy || benchRunning() || !conv.isGenerating() {
|
||||
t.Fatalf("bail de l'optimiseur : refus=%v bench=%v", conv.busyReason(), benchRunning())
|
||||
}
|
||||
if code, out := post(handleInternalLease, "/internal/v1/engine/lease", `{}`); code != 409 || out["error"] != errTuneBusy.Error() {
|
||||
t.Fatalf("second bail : %d %v", code, out)
|
||||
}
|
||||
if c := tuneCtx(); c["busy"] != errTuneBusy.Error() {
|
||||
t.Fatalf("contexte pendant l'optimisation : %v", c)
|
||||
}
|
||||
// Changer de discussion ne rompt pas le bail de l'optimiseur.
|
||||
conv.loadFrom("autre", nil)
|
||||
if !conv.isGenerating() || conv.busyReason() != errTuneBusy {
|
||||
t.Fatal("le bail de l'optimiseur a sauté à la bascule de discussion")
|
||||
}
|
||||
if code, _ := post(handleInternalLeaseRelease, "/internal/v1/engine/lease/release", `{"lease":"`+id+`"}`); code != 204 {
|
||||
t.Fatalf("libération : %d", code)
|
||||
}
|
||||
if conv.isGenerating() || conv.busyReason() == errTuneBusy {
|
||||
t.Fatal("bail rendu : le verrou devait être libre")
|
||||
}
|
||||
// Un benchmark de la façade : le contexte le dit en premier.
|
||||
code, out = post(handleInternalLease, "/internal/v1/engine/lease", `{"why":"bench"}`)
|
||||
if code != 200 {
|
||||
t.Fatalf("bail du bench : %d %v", code, out)
|
||||
}
|
||||
if c := tuneCtx(); c["busy"] != errBenchBusy.Error() {
|
||||
t.Fatalf("contexte pendant un bench : %v", c)
|
||||
}
|
||||
post(handleInternalLeaseRelease, "/internal/v1/engine/lease/release", `{"lease":"`+out["lease"].(string)+`"}`)
|
||||
|
||||
// Démarrage et arrêt sans le refus de l'optimiseur : la façade tient le
|
||||
// verrou.
|
||||
var guarded, osActs []string
|
||||
oldA, oldOS := internalServiceAction, internalServiceActionOS
|
||||
t.Cleanup(func() { internalServiceAction, internalServiceActionOS = oldA, oldOS })
|
||||
internalServiceAction = func(a string) error { guarded = append(guarded, a); return errTuneBusy }
|
||||
internalServiceActionOS = func(a string) error { osActs = append(osActs, a); return nil }
|
||||
for _, c := range []struct{ body, want string }{
|
||||
{`{"action":"stop","os":true}`, `{"error":"","ran":true}`},
|
||||
{`{"action":"start","os":true}`, `{"error":"","ran":true}`},
|
||||
{`{"action":"start"}`, `{"error":"` + errTuneBusy.Error() + `","ran":true}`},
|
||||
} {
|
||||
w := httptest.NewRecorder()
|
||||
handleInternalServiceAction(w, httptest.NewRequest("POST", "/internal/v1/service/action", strings.NewReader(c.body)))
|
||||
if got := strings.TrimSpace(w.Body.String()); w.Code != 200 || got != c.want {
|
||||
t.Fatalf("%s : %d %s", c.body, w.Code, got)
|
||||
}
|
||||
}
|
||||
if strings.Join(osActs, ",") != "stop,start" || strings.Join(guarded, ",") != "start" {
|
||||
t.Fatalf("actions : sans refus %v, avec %v", osActs, guarded)
|
||||
}
|
||||
|
||||
t.Setenv(internalTokenEnv, "")
|
||||
if facadeTune() {
|
||||
t.Fatal("tenu sans jeton interne")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,544 @@
|
||||
package loki
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"os"
|
||||
"sort"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// parity_tune_test.go — journal de référence de la partie PURE de
|
||||
// l'optimiseur (lot 28 de la migration Rust) : découpe et réécriture
|
||||
// d'EXTRA_ARGS, réglages par clé ou par drapeau, essais de chaque étape selon
|
||||
// la machine et les cases cochées, garde-fous (cœur de la ligne, dénature,
|
||||
// clés permises), diff et réécriture du preset, journal d'un essai, score et
|
||||
// départage. Rangé dans rust/loki-rs/tests/parity_tune/core.json ;
|
||||
// tests/tune_core.rs le rejoue.
|
||||
//
|
||||
// LOKI_PARITY_UPDATE=1 go test ./internal/loki -run TestPariteTuneCore
|
||||
|
||||
const parityTuneCoreFile = "../../rust/loki-rs/tests/parity_tune/core.json"
|
||||
|
||||
func parityTuneCands(c []tuneCand) []map[string]any {
|
||||
out := []map[string]any{}
|
||||
for _, x := range c {
|
||||
out = append(out, map[string]any{"stage": x.Stage, "label": x.Label, "cfg": x.Cfg})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func TestPariteTuneCore(t *testing.T) {
|
||||
journal := map[string]any{}
|
||||
|
||||
// --- EXTRA_ARGS ---------------------------------------------------------
|
||||
extras := []string{
|
||||
"", " ", "-b 2048", `--chat-template-file "/mes modèles/tpl.jinja" -ub 512`,
|
||||
`-ot 'blk\.(1[0-9])\.ffn_.*_exps\.=CPU' --n-cpu-moe 40`,
|
||||
`-ot "blk\.([0-9]+)\.ffn_.*_exps\.=CPU,per_layer_token_embd=CPU" --cache-type-k q8_0 --n-cpu-moe 40 ` +
|
||||
`--flash-attn on -ub 512 --chat-template-file "/a b/t.jinja" -ts 0.9,0.1 -ctv q8_0 -cmoe`,
|
||||
"-ub=1024 -t 8 -b 4096", " -ts 0.9,0.1 --flash-attn on", "-ts=1,1 -mg 0",
|
||||
"-ot exps=CPU,per_layer_token_embd=CPU -cmoe --cpu-moe -ncmoe=12",
|
||||
"-ot=per_layer_token_embd=CPU", "--override-tensor exps=CPU", "-ot", "-t", "-t 8 -t 6", "-ub",
|
||||
`"" -x`, `""x y`, `a""b`, `'a b'c "d"`, "--cache-type-k q8_0\t--flash-attn on\n-t 8",
|
||||
`"non fermé -b 4`, `x"y z"w -ub=1024`, "-bs", "--backend-sampling -t 4", "-b 512\t-ub 256",
|
||||
"-ncmoe", "--n-cpu-moe 0 --cpu-moe",
|
||||
}
|
||||
var ex []map[string]any
|
||||
for _, s := range extras {
|
||||
var spans [][]any
|
||||
for _, sp := range argSpans(s) {
|
||||
spans = append(spans, []any{sp.start, sp.end, sp.val})
|
||||
}
|
||||
dropped, removed := tuneExtraDropExperts(s)
|
||||
ex = append(ex, map[string]any{
|
||||
"in": s,
|
||||
"spans": spans,
|
||||
"split": splitArgs(s),
|
||||
"set_ub": tuneExtraSet(s, knobUBatch.flags, "2048"),
|
||||
"drop_ub": tuneExtraSet(s, knobUBatch.flags, ""),
|
||||
"set_t": tuneExtraSet(s, knobThreads.flags, "7"),
|
||||
"set_t_space": tuneExtraSet(s, knobThreads.flags, "a b"),
|
||||
"set_b": tuneExtraSet(s, knobBatch.flags, "4096"),
|
||||
"drop_ts": tuneExtraDrop(s, 1, "-ts", "--tensor-split"),
|
||||
"drop_cmoe": tuneExtraDrop(s, 0, "-cmoe", "--cpu-moe"),
|
||||
"add_bs": tuneExtraAddSwitch(s, "--backend-sampling"),
|
||||
"drop_experts": dropped,
|
||||
"removed": removed,
|
||||
"core": tuneCoreArgs(splitArgs(s), false),
|
||||
"core_optin": tuneCoreArgs(splitArgs(s), true),
|
||||
})
|
||||
}
|
||||
journal["extra"] = ex
|
||||
|
||||
// --- réglages ------------------------------------------------------------
|
||||
cfgs := []map[string]string{
|
||||
{},
|
||||
{"UBATCH": "1024", "BATCH": "4096", "THREADS": "0", "FIT_TARGET": "1536", "SPEC_N_MAX": "2"},
|
||||
{"EXTRA_ARGS": "-ub 512 -t 8", "UBATCH": "1024"},
|
||||
{"EXTRA_ARGS": "-ub=256 --threads 6 -b 1024 -fitt 2048 --spec-draft-n-max 5"},
|
||||
{"EXTRA_ARGS": "-ub 512", "UBATCH": " 128 "},
|
||||
{"EXTRA_ARGS": "-t"},
|
||||
tuneRichCfg(),
|
||||
}
|
||||
knobs := map[string]tuneKnob{"BATCH": knobBatch, "UBATCH": knobUBatch, "THREADS": knobThreads,
|
||||
"FIT_TARGET": knobFitTarget, "SPEC_N_MAX": knobSpecN}
|
||||
var kn []map[string]any
|
||||
for _, c := range cfgs {
|
||||
get, set, unset := map[string]string{}, map[string]any{}, map[string]any{}
|
||||
for name, k := range knobs {
|
||||
get[name] = k.get(c)
|
||||
set[name] = k.set(c, "99")
|
||||
unset[name] = k.set(c, "")
|
||||
}
|
||||
kn = append(kn, map[string]any{"cfg": c, "get": get, "set": set, "unset": unset})
|
||||
}
|
||||
journal["knobs"] = kn
|
||||
|
||||
// --- essais ---------------------------------------------------------------
|
||||
type envCase struct {
|
||||
name string
|
||||
env tuneEnv
|
||||
}
|
||||
rich := tuneRichEnv()
|
||||
envs := []envCase{
|
||||
{"riche", rich},
|
||||
{"sans placement", func() tuneEnv { e := tuneRichEnv(); e.Placement = false; return e }()},
|
||||
{"sans --fit", func() tuneEnv {
|
||||
e := tuneRichEnv()
|
||||
e.Help = strings.ReplaceAll(tuneTestHelp, "--fit", "--nofit")
|
||||
return e
|
||||
}()},
|
||||
{"sans --fit-target", func() tuneEnv {
|
||||
e := tuneRichEnv()
|
||||
e.Help = strings.ReplaceAll(tuneTestHelp, "--fit-target", "--fit-x")
|
||||
return e
|
||||
}()},
|
||||
{"sans nvidia-smi", func() tuneEnv { e := tuneRichEnv(); e.SMI = false; return e }()},
|
||||
{"sans opt-in", func() tuneEnv { e := tuneRichEnv(); e.OptIn = false; return e }()},
|
||||
{"une carte", func() tuneEnv { e := tuneRichEnv(); e.GPUs = 1; return e }()},
|
||||
{"trois cartes", func() tuneEnv { e := tuneRichEnv(); e.GPUs = 3; return e }()},
|
||||
{"cœurs inconnus", func() tuneEnv { e := tuneRichEnv(); e.PhysCores = 0; return e }()},
|
||||
{"deux cœurs", func() tuneEnv { e := tuneRichEnv(); e.PhysCores = 2; return e }()},
|
||||
{"environnement posé", func() tuneEnv {
|
||||
e := tuneRichEnv()
|
||||
e.UserEnv = map[string]string{"GGML_OP_OFFLOAD_MIN_BATCH": "64", "GGML_CUDA_GRAPH_OPT": "1"}
|
||||
e.QueuesEnv = true
|
||||
e.ArgEnv = map[string]string{"LLAMA_ARG_BACKEND_SAMPLING": "1"}
|
||||
return e
|
||||
}()},
|
||||
{"dense deux cartes", tuneEnv{Help: tuneTestHelp, GPUs: 2, VRAMMiB: 28 << 10, ModelBytes: 10 << 30, SMI: true,
|
||||
PhysCores: 8, Placement: true, OptIn: true}},
|
||||
{"modèle plus gros que la VRAM", tuneEnv{Help: tuneTestHelp, GPUs: 1, VRAMMiB: 8 << 10, ModelBytes: 20 << 30, SMI: true,
|
||||
PhysCores: 8}},
|
||||
{"moteur ancien", tuneEnv{GPUs: 1, SMI: true, PhysCores: 4, Placement: true, OptIn: true}},
|
||||
}
|
||||
candCfgs := []struct {
|
||||
name string
|
||||
cfg map[string]string
|
||||
}{
|
||||
{"riche", tuneRichCfg()},
|
||||
{"simple", map[string]string{"MODEL": "m.gguf", "CTX": "32768"}},
|
||||
{"contexte non chiffré", map[string]string{"MODEL": "m.gguf", "EXTRA_ARGS": "-ot exps=CPU"}},
|
||||
{"split tensor", map[string]string{"MODEL": "m.gguf", "CTX": "32768", "SPLIT_MODE": "tensor", "EXTRA_ARGS": "-ts 1,1"}},
|
||||
{"lots posés", map[string]string{"MODEL": "m.gguf", "CTX": "8192", "UBATCH": "1024", "BATCH": "2048",
|
||||
"OP_OFFLOAD_MIN_BATCH": "128", "CUDA_LAUNCH_QUEUES": "4X", "THREADS": "7", "FIT_TARGET": "1536"}},
|
||||
{"spéculation", map[string]string{"MODEL": "m.gguf", "CTX": "8192", "SPEC": "draft", "SPEC_N_MAX": "4",
|
||||
"CUDA_GRAPH_OPT": "On", "EXTRA_ARGS": "--n-cpu-moe 10 -bs"}},
|
||||
{"ngram", map[string]string{"MODEL": "m.gguf", "CTX": "8192", "SPEC": "ngram"}},
|
||||
{"cpu-moe", map[string]string{"MODEL": "m.gguf", "CTX": "16384", "EXTRA_ARGS": "-cmoe -t 0"}},
|
||||
}
|
||||
var cs []map[string]any
|
||||
for _, cc := range candCfgs {
|
||||
for _, ec := range envs {
|
||||
stages := map[string]any{}
|
||||
for _, st := range tuneStages {
|
||||
c, why := st.Gen(cc.cfg, ec.env)
|
||||
stages[st.Name] = map[string]any{"why": why, "cands": parityTuneCands(c)}
|
||||
}
|
||||
e := ec.env
|
||||
cs = append(cs, map[string]any{"cfg_name": cc.name, "env_name": ec.name, "cfg": cc.cfg,
|
||||
"env": map[string]any{"help": e.Help, "gpus": e.GPUs, "vram_mib": e.VRAMMiB, "model_bytes": e.ModelBytes,
|
||||
"moe": e.MoE, "phys_cores": e.PhysCores, "smi": e.SMI, "arg_env": e.ArgEnv, "user_env": e.UserEnv,
|
||||
"queues_env": e.QueuesEnv, "placement": e.Placement, "opt_in": e.OptIn},
|
||||
"weights_on_cpu": tuneWeightsOnCPU(cc.cfg, ec.env),
|
||||
"stages": stages})
|
||||
}
|
||||
}
|
||||
journal["cands"] = cs
|
||||
var sw []map[string]any
|
||||
for _, name := range []string{"placement", "marges", "lots", "délestage", "threads", "files CUDA", "opt-in"} {
|
||||
for _, only := range [][]string{nil, {"lots"}, {"Délestage"}, {"files"}, {"FILES CUDA"}, {"marges-x"}, {" threads "}, {"opt"}, {"x"}} {
|
||||
sw = append(sw, map[string]any{"name": name, "only": only, "wanted": tuneStageWanted(name, only)})
|
||||
}
|
||||
}
|
||||
journal["stage_wanted"] = sw
|
||||
|
||||
// --- garde-fous ------------------------------------------------------------
|
||||
base := tuneLaunch{Args: []string{"/bin/llama-server", "-m", "/m.gguf", "-c", "65536", "-b", "2048", "-ub", "512",
|
||||
"--host", "127.0.0.1", "--port", "41000", "--parallel", "1", "-ctk", "q8_0", "-ot", "exps=CPU,per_layer_token_embd=CPU",
|
||||
"--cache-ram", "8192", "--flash-attn", "on"},
|
||||
Env: map[string]string{"CUDA_VISIBLE_DEVICES": "1,0", "CUDA_SCALE_LAUNCH_QUEUES": "4x"}}
|
||||
ok := tuneLaunch{Args: []string{"/bin/llama-server", "-m", "/m.gguf", "-c", "65536", "-b", "4096", "-ub", "2048",
|
||||
"--host", "127.0.0.1", "--port", "41001", "--parallel", "1", "-ctk", "q8_0", "-ot", "per_layer_token_embd=CPU",
|
||||
"--cache-ram", "12000", "--flash-attn", "on", "-t", "7"},
|
||||
Env: map[string]string{"CUDA_VISIBLE_DEVICES": "1,0", "GGML_OP_OFFLOAD_MIN_BATCH": "128"}}
|
||||
clone := func(l tuneLaunch) tuneLaunch {
|
||||
c := tuneLaunch{Args: append([]string(nil), l.Args...), Env: map[string]string{}}
|
||||
for k, v := range l.Env {
|
||||
c.Env[k] = v
|
||||
}
|
||||
return c
|
||||
}
|
||||
var dn []map[string]any
|
||||
add := func(name string, b, c tuneLaunch) {
|
||||
dn = append(dn, map[string]any{"name": name, "base": b, "cand": c,
|
||||
"denature": tuneDenature(b, c, false), "denature_optin": tuneDenature(b, c, true),
|
||||
"same_key": tuneLaunchKey(b) == tuneLaunchKey(c)})
|
||||
}
|
||||
add("réglages permis", base, ok)
|
||||
add("identique", base, clone(base))
|
||||
muts := map[string]func(l *tuneLaunch){
|
||||
"contexte": func(l *tuneLaunch) { l.Args[4] = "32768" },
|
||||
"cache kv": func(l *tuneLaunch) { l.Args[16] = "f16" },
|
||||
"ot": func(l *tuneLaunch) { l.Args[18] = "exps=CPU" },
|
||||
"fa": func(l *tuneLaunch) { l.Args[len(l.Args)-3] = "off" },
|
||||
"slots": func(l *tuneLaunch) { l.Args[14] = "2" },
|
||||
"cuda": func(l *tuneLaunch) { l.Env["CUDA_VISIBLE_DEVICES"] = "0,1" },
|
||||
"graphes": func(l *tuneLaunch) { l.Env["GGML_CUDA_GRAPH_OPT"] = "1" },
|
||||
"spéculation": func(l *tuneLaunch) { l.Args = append(l.Args, "--spec-draft-n-max", "4") },
|
||||
"modèle ébauche": func(l *tuneLaunch) {
|
||||
l.Args = append(l.Args, "-md", "/d.gguf")
|
||||
},
|
||||
"argument de plus": func(l *tuneLaunch) { l.Args = append(l.Args, "--jinja") },
|
||||
"argument de moins": func(l *tuneLaunch) {
|
||||
l.Args = l.Args[:len(l.Args)-2]
|
||||
},
|
||||
"port et clé": func(l *tuneLaunch) {
|
||||
l.Args = append(l.Args, "--api-key", "s3cret", "--slot-save-path", "/tmp/x", "--port=9")
|
||||
},
|
||||
"cache-ram": func(l *tuneLaunch) { l.Args = append(l.Args, "-cram", "4096") },
|
||||
}
|
||||
names := make([]string, 0, len(muts))
|
||||
for n := range muts {
|
||||
names = append(names, n)
|
||||
}
|
||||
sort.Strings(names)
|
||||
for _, name := range names {
|
||||
c := clone(ok)
|
||||
muts[name](&c)
|
||||
add(name, base, c)
|
||||
}
|
||||
journal["denature"] = dn
|
||||
|
||||
rc := tuneRichCfg()
|
||||
var cc []map[string]any
|
||||
check := func(name string, b, c map[string]string) {
|
||||
e1, e2 := tuneCfgCheck(b, c, false), tuneCfgCheck(b, c, true)
|
||||
s1, s2 := "", ""
|
||||
if e1 != nil {
|
||||
s1 = e1.Error()
|
||||
}
|
||||
if e2 != nil {
|
||||
s2 = e2.Error()
|
||||
}
|
||||
cc = append(cc, map[string]any{"name": name, "base": b, "cand": c, "check": s1, "check_optin": s2,
|
||||
"diff": tuneDiff(b, c)})
|
||||
}
|
||||
check("identique", rc, copyCfg(rc))
|
||||
check("lots", rc, setKey(setKey(rc, "UBATCH", "2048"), "BATCH", "4096"))
|
||||
check("contexte", rc, setKey(rc, "CTX", "32768"))
|
||||
check("spec", rc, setKey(rc, "SPEC", "auto"))
|
||||
check("graphes", rc, setKey(rc, "CUDA_GRAPH_OPT", "on"))
|
||||
check("retrait", rc, setKey(rc, "TEMP", ""))
|
||||
check("extra permis", rc, knobThreads.set(rc, "4"))
|
||||
check("extra interdit", rc, setKey(rc, "EXTRA_ARGS", strings.Replace(rc["EXTRA_ARGS"], "q8_0", "f16", 1)))
|
||||
check("extra placement", rc, setKey(rc, "EXTRA_ARGS", func() string { s, _ := tuneExtraDropExperts(rc["EXTRA_ARGS"]); return s }()))
|
||||
check("spéculation dans extra", rc, setKey(rc, "EXTRA_ARGS", rc["EXTRA_ARGS"]+" --spec-draft-n-max 4"))
|
||||
check("extra vide", map[string]string{"EXTRA_ARGS": "-t 8"}, map[string]string{})
|
||||
journal["cfg_check"] = cc
|
||||
|
||||
content := "# NAME=Gros MoE\n# commentaire\nMODEL=big.gguf\nCTX=65536\nUBATCH=512\n" +
|
||||
`EXTRA_ARGS="--cache-type-k q8_0 --flash-attn on -t 8"` + "\n"
|
||||
pb := parseEnv(content)
|
||||
var pp []map[string]any
|
||||
patch := func(name string, win map[string]string) {
|
||||
out, err := tunePatchPreset(content, pb, win)
|
||||
e := ""
|
||||
if err != nil {
|
||||
e = err.Error()
|
||||
}
|
||||
pp = append(pp, map[string]any{"name": name, "win": win, "out": out, "error": e})
|
||||
}
|
||||
patch("threads retirés, lots", setKey(setKey(knobThreads.set(pb, ""), "UBATCH", "2048"), "BATCH", "4096"))
|
||||
patch("contexte", setKey(pb, "CTX", "32768"))
|
||||
patch("rien", copyCfg(pb))
|
||||
patch("opt-in", setKey(pb, "SPEC", "auto"))
|
||||
patch("retrait d'EXTRA_ARGS", setKey(pb, "EXTRA_ARGS", ""))
|
||||
journal["patch"] = struct {
|
||||
Content string `json:"content"`
|
||||
Cases []map[string]any `json:"cases"`
|
||||
}{content, pp}
|
||||
|
||||
// --- journal d'un essai ------------------------------------------------------
|
||||
logs := []string{
|
||||
"load_tensors: offloaded 40/49 layers to GPU\n" +
|
||||
"llama_kv_cache: size = 1024.00 MiB ( 8192 cells, 32 layers, 1/1 seqs), K (q8_0): 512.00 MiB, V (q8_0): 512.00 MiB\n" +
|
||||
"load_tensors: offloaded 49/49 layers to GPU\n",
|
||||
"rien",
|
||||
"",
|
||||
"K (F16): 1 MiB, V (f16): 1 MiB\nK (q4_0): 1, V (q8_0): 2\nK (f16): x V (f16): y",
|
||||
"ggml_backend_cuda_buffer_type_alloc_buffer: cudaMalloc failed: out of memory",
|
||||
"common_fit: failed to fit model\n",
|
||||
"llama_model_load: error loading model: bad magic\n",
|
||||
"ligne 1\nderniere ligne de journal \n\n",
|
||||
"\n \n",
|
||||
"x\n" + strings.Repeat("é", 100),
|
||||
"x\n" + strings.Repeat("a", 159) + "é" + strings.Repeat("b", 20),
|
||||
}
|
||||
var lf []map[string]any
|
||||
for _, l := range logs {
|
||||
off, total, kv := tuneLogFacts(l)
|
||||
lf = append(lf, map[string]any{"log": l, "offloaded": off, "total": total, "kv": kv, "failure": tuneLoadFailure(l)})
|
||||
}
|
||||
journal["logs"] = lf
|
||||
|
||||
// --- score et départage ------------------------------------------------------
|
||||
intp := func(n int) *int { return &n }
|
||||
var recSets []map[string]any
|
||||
weights := func(name string, recs []perfRec) {
|
||||
recSets = append(recSets, map[string]any{"name": name, "recs": recs, "weights": tuneWeightsFrom(recs)})
|
||||
}
|
||||
weights("vide", nil)
|
||||
var few []perfRec
|
||||
for i := 0; i < 19; i++ {
|
||||
few = append(few, perfRec{Kind: perfMain, Complete: true, New: 1000 + i, Gen: 300})
|
||||
}
|
||||
weights("trop peu", few)
|
||||
var many []perfRec
|
||||
for i := 0; i < 30; i++ {
|
||||
r := perfRec{Kind: perfMain, Complete: true, New: 500 + 37*i, Gen: 100 + 13*i, Total: 4000 + 100*i}
|
||||
if i%3 == 0 {
|
||||
r.Cached = intp(100)
|
||||
} else {
|
||||
r.Cached = intp(r.Total - 200)
|
||||
}
|
||||
many = append(many, r)
|
||||
}
|
||||
many = append(many, perfRec{Kind: perfBench, Complete: true, New: 99999, Gen: 99999},
|
||||
perfRec{Kind: perfMain, Complete: false, New: 99999, Gen: 99999})
|
||||
weights("télémétrie", many)
|
||||
var bounds []perfRec
|
||||
for i := 0; i < 21; i++ {
|
||||
bounds = append(bounds, perfRec{Kind: perfTask, Complete: true, New: 50, Gen: 9000, Total: 100, Cached: intp(0)})
|
||||
}
|
||||
weights("bornes", bounds)
|
||||
var even []perfRec
|
||||
for i := 0; i < 20; i++ {
|
||||
even = append(even, perfRec{Kind: perfMain, Complete: true, New: 1000 + 10*i, Gen: 200 + i, Total: 2048, Cached: intp(204)})
|
||||
}
|
||||
weights("pair, froid connu", even)
|
||||
journal["weights"] = recSets
|
||||
|
||||
w := tuneWeights{K: 2000, G: 600, FCold: 0.05}
|
||||
deep := func() *benchResult {
|
||||
return &benchResult{PromptPerSecond: 1000, PredictedPerSec: 50, Depth: &benchDepth{Target: 32768,
|
||||
Cold: &benchTurn{PromptPerSecond: 800},
|
||||
DecodePerSec: 40, CachedPerSec: 999,
|
||||
Turns: []benchTurn{{New: 2100, Cached: 30000, Expected: 30048, PromptMs: 2000},
|
||||
{New: 2100, Cached: 32300, Expected: 32348, PromptMs: 2000}}}}
|
||||
}
|
||||
var runs []map[string]any
|
||||
score := func(name string, r *benchResult) {
|
||||
run, err := tuneRunFrom(r, w)
|
||||
e := ""
|
||||
if err != nil {
|
||||
e = err.Error()
|
||||
}
|
||||
runs = append(runs, map[string]any{"name": name, "bench": r, "run": run, "error": e})
|
||||
}
|
||||
score("complet", deep())
|
||||
score("vide", nil)
|
||||
score("sans decode", &benchResult{PromptPerSecond: 1000})
|
||||
score("rapide", &benchResult{PromptPerSecond: 1000, PredictedPerSec: 50})
|
||||
score("profondeur sautée", &benchResult{PromptPerSecond: 1000, PredictedPerSec: 50, Depth: &benchDepth{Skipped: "petit"}})
|
||||
score("partiel", func() *benchResult { r := deep(); r.Depth.Partial = "contexte plein"; return r }())
|
||||
score("sans froid", func() *benchResult { r := deep(); r.Depth.Cold = nil; return r }())
|
||||
score("froid nul", func() *benchResult { r := deep(); r.Depth.Cold.PromptPerSecond = 0; return r }())
|
||||
score("sans tours", func() *benchResult { r := deep(); r.Depth.Turns = nil; return r }())
|
||||
score("sans decode à D", func() *benchResult { r := deep(); r.Depth.DecodePerSec = 0; return r }())
|
||||
score("cache inconnu", func() *benchResult { r := deep(); r.Depth.Turns[1].Cached = -1; return r }())
|
||||
score("cache inconnu, rien d'autre", func() *benchResult {
|
||||
r := deep()
|
||||
r.Depth.Turns[1].Cached = -1
|
||||
r.Depth.CachedPerSec = 0
|
||||
return r
|
||||
}())
|
||||
score("rien de neuf", func() *benchResult {
|
||||
r := deep()
|
||||
for i := range r.Depth.Turns {
|
||||
r.Depth.Turns[i].New = 48
|
||||
}
|
||||
return r
|
||||
}())
|
||||
journal["runs"] = runs
|
||||
|
||||
var wn []map[string]any
|
||||
for _, c := range [][2][]float64{
|
||||
{{20, 20.4}, {19.7, 19.8}}, {{20, 20.4}, {18}}, {{20, 20.4}, {18, 18.1}}, {{18, 22}, {18.5, 18.6}},
|
||||
{{}, {1, 2}}, {{10}, {}}, {{10, 10}, {9.6, 9.6}}, {{10, 10}, {9.7, 9.7}}, {{0}, {1, 1}}, {{10, 12}, {8, 8.2, 8.1}},
|
||||
} {
|
||||
gain, need, ok := tuneWins(c[0], c[1])
|
||||
wn = append(wn, map[string]any{"base": c[0], "cand": c[1], "gain": gain, "need": need, "wins": ok,
|
||||
"spread_base": tuneSpread(c[0]), "mean_cand": tuneMean(c[1])})
|
||||
}
|
||||
journal["wins"] = wn
|
||||
var wr []map[string]any
|
||||
for _, c := range []struct {
|
||||
base []float64
|
||||
first float64
|
||||
}{{[]float64{20, 20.4}, 19}, {[]float64{20, 20.4}, 19.8}, {[]float64{20}, 19.39}, {[]float64{20}, 19.41}, {nil, 1}} {
|
||||
wr = append(wr, map[string]any{"base": c.base, "first": c.first, "worth": tuneWorthRepeat(c.base, c.first)})
|
||||
}
|
||||
journal["worth_repeat"] = wr
|
||||
|
||||
var hr []map[string]any
|
||||
for _, c := range []struct {
|
||||
gpus []gpuStat
|
||||
visible []int
|
||||
}{
|
||||
{nil, nil},
|
||||
{[]gpuStat{{Total: 24576, Used: 20000}, {Total: 12288, Used: 1000}}, nil},
|
||||
{[]gpuStat{{Total: 24576, Used: 20000}, {Total: 12288, Used: 1000}}, []int{1}},
|
||||
{[]gpuStat{{Total: 0, Used: 0}, {Total: 8192, Used: 9000}}, nil},
|
||||
{[]gpuStat{{Total: 8192, Used: 100}}, []int{3}},
|
||||
} {
|
||||
free, ok := tuneHeadroom(c.gpus, c.visible)
|
||||
var g [][2]int
|
||||
for _, x := range c.gpus {
|
||||
g = append(g, [2]int{x.Total, x.Used})
|
||||
}
|
||||
hr = append(hr, map[string]any{"gpus": g, "visible": c.visible, "free": free, "ok": ok})
|
||||
}
|
||||
journal["headroom"] = hr
|
||||
var vg []map[string]any
|
||||
for _, s := range []string{"", "0", "1,0", " 2 , 3 ", "GPU-abc", "0,,1", "+1,-2"} {
|
||||
vg = append(vg, map[string]any{"in": s, "out": tuneVisibleGPUs(map[string]string{"CUDA_VISIBLE_DEVICES": s})})
|
||||
}
|
||||
journal["visible"] = vg
|
||||
var fa []map[string]any
|
||||
for _, a := range [][]string{
|
||||
{"/b", "--host", "0.0.0.0", "--port", "8080", "-m", "x"},
|
||||
{"/b", "--host=::", "--port=1", "--port", "2", "--host"},
|
||||
{"/b", "--hostname", "x", "-p", "3"},
|
||||
} {
|
||||
fa = append(fa, map[string]any{"in": a, "out": tuneForceAddr(a, "127.0.0.1", "41234")})
|
||||
}
|
||||
journal["force_addr"] = fa
|
||||
|
||||
// --- configuration d'un essai --------------------------------------------------
|
||||
var tc []map[string]any
|
||||
for _, c := range []map[string]string{
|
||||
{"MODEL": "m.gguf", "EXTRA_ARGS": `-ot "a b" -t 8`, "PORT": "41000"},
|
||||
{"MODEL": "x\ny"},
|
||||
{"NAME": "é ü", "A": " b "},
|
||||
{"A": `"q"`, "B": "c'd", "C": "#h"},
|
||||
} {
|
||||
dir := t.TempDir()
|
||||
err := writeTuneTrialConfig(dir, c)
|
||||
e, text := "", ""
|
||||
if err != nil {
|
||||
e = err.Error()
|
||||
} else {
|
||||
b, _ := os.ReadFile(dir + "/config.env")
|
||||
text = string(b)
|
||||
}
|
||||
tc = append(tc, map[string]any{"cfg": c, "error": e, "text": text})
|
||||
}
|
||||
journal["trial_config"] = tc
|
||||
|
||||
// --- Verrou : contenu du fichier, clé de prise, binaires -----------------
|
||||
owners := []tuneOwner{
|
||||
{Owner: tuneProc{PID: 42}, Via: "web", Phase: "essais", Since: 1700000000},
|
||||
{Owner: tuneProc{PID: 42, Start: "b0c1/123", Exes: []string{"/usr/bin/loki-rs"}}, Via: "apply",
|
||||
Phase: "application", Since: 1700000000, Nonce: 1700000000123456789,
|
||||
Trial: &tuneProc{PID: 43, Start: "b0c1/456", Exes: []string{"/usr/bin/loki", "/opt/llama-server"}},
|
||||
MainWasActive: true, Backup: "/home/l/tune/backup/Dense-1.env", PresetID: "Dense", PresetName: "Dense"},
|
||||
}
|
||||
lk := []map[string]any{}
|
||||
for _, o := range owners {
|
||||
b, _ := json.Marshal(o)
|
||||
lk = append(lk, map[string]any{"json": string(b), "key": tuneHeldKey(o)})
|
||||
}
|
||||
journal["lock_owners"] = lk
|
||||
se := []map[string]any{}
|
||||
for _, e := range [][2]string{
|
||||
{"/usr/local/bin/loki", "/usr/local/bin/loki (deleted)"}, {"/usr/local/bin/loki", "/usr/bin/llama-server"},
|
||||
{`C:\Loki\loki.exe`, "LOKI"}, {"", "loki"}, {"/a/llama-server", "llama-server"}, {"/a/b/", "b"},
|
||||
} {
|
||||
se = append(se, map[string]any{"a": e[0], "b": e[1], "same": sameExe(e[0], e[1])})
|
||||
}
|
||||
journal["same_exe"] = se
|
||||
|
||||
// --- Résultat tel qu'enregistré et montré --------------------------------
|
||||
run := tuneRun{TurnSec: 3.25, ColdPP: 812.5, CachedPP: 1500, TG: 42.75, ProsePP: 2000, ProseTG: 45.5, Depth: 8192}
|
||||
results := []tuneResult{{}, {
|
||||
PresetID: "Dense", PresetName: "Dense", BaseFP: "abc", PresetFP: "def", Engine: "b7000-x", EngineBuild: 7000,
|
||||
Weights: tuneWeights{K: 2000, G: 600, FCold: 0.05, From: "défaut"}, Depth: 8192, NCtx: 16384, Slots: 1,
|
||||
Baseline: tuneTrial{Stage: "référence", Label: "configuration actuelle", Status: "mesuré",
|
||||
Runs: []tuneRun{run, {TurnSec: 3.5, ProsePP: 1900, ProseTG: 44}}, TurnSec: 3.375, Headroom: -1, Sec: 61.5,
|
||||
Offloaded: "33/33"},
|
||||
Trials: []tuneTrial{
|
||||
{Stage: "lots", Label: "UBATCH=512 BATCH=1024", Status: "retenu", Why: "−7.3 % par tour (seuil 3.0 %)",
|
||||
Runs: []tuneRun{run}, TurnSec: 3.125, Gain: 0.0734, Headroom: 512, Changes: []string{"UBATCH 2048 → 512"}, Sec: 30},
|
||||
{Stage: "lots", Label: "UBATCH=2048 BATCH=4096", Status: "écarté", Why: "dénature : x", Headroom: -1},
|
||||
},
|
||||
Best: "UBATCH=512 BATCH=1024", Gain: 0.0734, Set: map[string]string{"UBATCH": "512", "BATCH": "1024"},
|
||||
Old: map[string]string{"UBATCH": "2048", "BATCH": ""}, Changes: []string{"UBATCH 2048 → 512", "BATCH + 1024"},
|
||||
Placement: true, Partial: "annulé", Skipped: []string{"marges : une seule carte"}, Notes: []string{"n"},
|
||||
OptIn: true, At: 1700000000,
|
||||
}}
|
||||
rs := []string{}
|
||||
for _, r := range results {
|
||||
b, _ := json.Marshal(r)
|
||||
rs = append(rs, string(b))
|
||||
}
|
||||
journal["results"] = rs
|
||||
|
||||
// --- Après application : la configuration est-elle l'essai retenu ? ------
|
||||
ab := map[string]string{"MODEL": "m.gguf", "UBATCH": "512", "EXTRA_ARGS": "-t 8"}
|
||||
ares := &tuneResult{BaseFP: configFingerprint(ab), Set: map[string]string{"UBATCH": "2048", "EXTRA_ARGS": ""},
|
||||
Old: map[string]string{"UBATCH": "512", "EXTRA_ARGS": "-t 8"}}
|
||||
ap := []map[string]any{}
|
||||
for _, now := range []map[string]string{
|
||||
{"MODEL": "m.gguf", "UBATCH": "2048"}, {"MODEL": "m.gguf", "UBATCH": "1024"},
|
||||
{"MODEL": "autre.gguf", "UBATCH": "2048"}, {"MODEL": "m.gguf", "UBATCH": "2048", "EXTRA_ARGS": "-t 4"},
|
||||
{"MODEL": "m.gguf", "UBATCH": "2048", "PORT": "9"},
|
||||
} {
|
||||
ap = append(ap, map[string]any{"now": now, "why": tuneAppliedMismatch(now, ares)})
|
||||
}
|
||||
journal["applied"] = map[string]any{"base_fp": ares.BaseFP, "set": ares.Set, "old": ares.Old, "cases": ap}
|
||||
|
||||
got, err := parityJSON(journal)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if os.Getenv("LOKI_PARITY_UPDATE") == "1" {
|
||||
if err := os.MkdirAll("../../rust/loki-rs/tests/parity_tune", 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := os.WriteFile(parityTuneCoreFile, got, 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return
|
||||
}
|
||||
want, err := os.ReadFile(parityTuneCoreFile)
|
||||
if err != nil {
|
||||
t.Fatalf("journal de référence absent (%v) : LOKI_PARITY_UPDATE=1 pour le créer", err)
|
||||
}
|
||||
if string(got) != string(want) {
|
||||
t.Errorf("l'optimiseur ne produit plus le journal rangé dans %s.\n"+
|
||||
"Si c'est voulu : LOKI_PARITY_UPDATE=1 go test ./internal/loki -run TestPariteTuneCore,\n"+
|
||||
"puis cargo test --test tune_core dit si le port Rust suit.", parityTuneCoreFile)
|
||||
}
|
||||
}
|
||||
@@ -133,6 +133,8 @@ func withInternalAPI(next http.Handler) http.Handler {
|
||||
handleInternalSideJob(w, r)
|
||||
case "/internal/v1/bench/perf":
|
||||
handleInternalBenchPerf(w, r)
|
||||
case "/internal/v1/tune/context":
|
||||
handleInternalTuneContext(w, r)
|
||||
case "/internal/v1/tasks/run":
|
||||
handleInternalTaskRun(w, r)
|
||||
case "/internal/v1/push/send":
|
||||
|
||||
@@ -44,9 +44,11 @@ type extLeaseState struct {
|
||||
stop bool
|
||||
ttl time.Duration
|
||||
timer *time.Timer
|
||||
// bench : le bail d'un benchmark de la façade (LOKI_BENCH=rust) — les
|
||||
// autres reçoivent errBenchBusy, et changer de discussion ne le rompt pas.
|
||||
bench bool
|
||||
// why : le motif d'un bail de mesure de la façade — errBenchBusy pour un
|
||||
// benchmark (LOKI_BENCH=rust), errTuneBusy pour l'optimiseur
|
||||
// (LOKI_TUNE=rust). Les autres reçoivent ce refus, et changer de
|
||||
// discussion ne rompt pas le bail. nil : un tour ordinaire.
|
||||
why error
|
||||
}
|
||||
|
||||
// extLeaseClearLocked oublie le bail de la façade. c.mu détenu.
|
||||
@@ -57,7 +59,7 @@ var benchLeaseHeld atomic.Bool
|
||||
|
||||
func (c *Conversation) extLeaseClearLocked() {
|
||||
if c.extLease != nil {
|
||||
if c.extLease.bench {
|
||||
if c.extLease.why == errBenchBusy {
|
||||
benchLeaseHeld.Store(false)
|
||||
}
|
||||
c.extLease.timer.Stop()
|
||||
@@ -65,8 +67,9 @@ func (c *Conversation) extLeaseClearLocked() {
|
||||
}
|
||||
}
|
||||
|
||||
// extLeaseAcquire prend le verrou de génération pour la façade.
|
||||
func (c *Conversation) extLeaseAcquire(ttl time.Duration, bench bool) (string, error) {
|
||||
// extLeaseAcquire prend le verrou de génération pour la façade ; why : voir
|
||||
// extLeaseState.
|
||||
func (c *Conversation) extLeaseAcquire(ttl time.Duration, why error) (string, error) {
|
||||
if err := tuneGuard(); err != nil {
|
||||
return "", err
|
||||
}
|
||||
@@ -79,12 +82,12 @@ func (c *Conversation) extLeaseAcquire(ttl time.Duration, bench bool) (string, e
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
st := &extLeaseState{id: fmt.Sprintf("%x", b), ttl: ttl, bench: bench}
|
||||
st := &extLeaseState{id: fmt.Sprintf("%x", b), ttl: ttl, why: why}
|
||||
st.timer = time.AfterFunc(ttl, func() { c.extLeaseExpire(st) })
|
||||
c.Generating = true
|
||||
if bench {
|
||||
c.benching, c.leaseWhy = true, errBenchBusy
|
||||
benchLeaseHeld.Store(true)
|
||||
if why != nil {
|
||||
c.benching, c.leaseWhy = true, why
|
||||
benchLeaseHeld.Store(why == errBenchBusy)
|
||||
}
|
||||
c.cancel = func() {
|
||||
c.mu.Lock()
|
||||
@@ -104,7 +107,7 @@ func (c *Conversation) extLeaseExpire(st *extLeaseState) {
|
||||
}
|
||||
c.extLease = nil
|
||||
c.Generating, c.cancel = false, nil
|
||||
if st.bench {
|
||||
if st.why != nil {
|
||||
c.benching, c.leaseWhy = false, nil
|
||||
benchLeaseHeld.Store(false)
|
||||
}
|
||||
@@ -130,7 +133,7 @@ func (c *Conversation) extLeaseRelease(id string) {
|
||||
if c.extLease == nil || c.extLease.id != id {
|
||||
return
|
||||
}
|
||||
if c.extLease.bench {
|
||||
if c.extLease.why != nil {
|
||||
c.benching, c.leaseWhy = false, nil
|
||||
}
|
||||
c.extLeaseClearLocked()
|
||||
@@ -161,7 +164,7 @@ func readLeaseBody(w http.ResponseWriter, r *http.Request, v any) bool {
|
||||
func handleInternalLease(w http.ResponseWriter, r *http.Request) {
|
||||
var in struct {
|
||||
TTLms int64 `json:"ttl_ms"`
|
||||
Why string `json:"why"` // "bench" : le bail d'un benchmark
|
||||
Why string `json:"why"` // "bench" : un benchmark ; "tune" : l'optimiseur
|
||||
}
|
||||
if !readLeaseBody(w, r, &in) {
|
||||
return
|
||||
@@ -170,7 +173,14 @@ func handleInternalLease(w http.ResponseWriter, r *http.Request) {
|
||||
if in.TTLms > 0 {
|
||||
ttl = min(max(time.Duration(in.TTLms)*time.Millisecond, extLeaseMinTTL), extLeaseMaxTTL)
|
||||
}
|
||||
id, err := conv.extLeaseAcquire(ttl, in.Why == "bench")
|
||||
var why error
|
||||
switch in.Why {
|
||||
case "bench":
|
||||
why = errBenchBusy
|
||||
case "tune":
|
||||
why = errTuneBusy
|
||||
}
|
||||
id, err := conv.extLeaseAcquire(ttl, why)
|
||||
if err != nil {
|
||||
if err == ErrBusy {
|
||||
err = conv.busyReason() // dit QUI occupe le moteur
|
||||
|
||||
@@ -86,7 +86,7 @@ func TestBailInterneVerrouPartage(t *testing.T) {
|
||||
func TestBailInterneNeLibereQueLeSien(t *testing.T) {
|
||||
testHome(t)
|
||||
libérerVerrou(t)
|
||||
id, err := conv.extLeaseAcquire(time.Minute, false)
|
||||
id, err := conv.extLeaseAcquire(time.Minute, nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -110,7 +110,7 @@ func TestBailInterneNeLibereQueLeSien(t *testing.T) {
|
||||
func TestBailInterneExpire(t *testing.T) {
|
||||
testHome(t)
|
||||
libérerVerrou(t)
|
||||
id, err := conv.extLeaseAcquire(50*time.Millisecond, false)
|
||||
id, err := conv.extLeaseAcquire(50*time.Millisecond, nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user