url/colibri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #301 from NeuralNotwerk/pr/pin-auto

Browse Source 
PIN=auto: seed the pin from the live usage history
This commit is contained in:
Vincenzo
2026-07-16 12:38:09 +02:00
committed by GitHub
parent 35f90b9e76 81c0398877
commit 0d297ee85b
2 changed files with 22 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/glm.c
+21 -2
View File
@@ -5967,8 +5967,27 @@ int main(int argc, char **argv){
/* HOT-STORE: PIN=<statsfile> [PIN_GB=g] -> top expert per frequenza fissi in RAM.
* Va PRIMA di cap_for_ram: i pinnati contano nel residente. */
if(getenv("PIN")){
const char *pin_gb=getenv("PIN_GB");
pin_load(&m,getenv("PIN"),pin_gb&&!strcmp(pin_gb,"all")?-1.0:pin_gb?atof(pin_gb):10.0); /* PIN_GB=all (#80) */
const char *pin=getenv("PIN"); char pauto[2100];
if(!strcmp(pin,"auto")){
/* PIN=auto: la storia VIVA <SNAP>/.coli_usage (appesa a ogni turno) batte il
* profilo congelato stats.txt — il pin di ogni riavvio riflette il carico reale
* accumulato, non il prompt di bootstrap. Fallback stats.txt per una dir vergine;
* nessuno dei due -> nessun pin (AUTOPIN piu' sotto resta escluso: PIN e' settato).
* EN: prefer the live usage history over the frozen one-shot profile, so each
* reload's pin placement follows the accumulated real workload. */
snprintf(pauto,sizeof(pauto),"%s/.coli_usage",snap);
FILE *pf=fopen(pauto,"rb"); long psz=0;
if(pf){ fseek(pf,0,SEEK_END); psz=ftell(pf); fclose(pf); }
if(psz<=0){ snprintf(pauto,sizeof(pauto),"%s/stats.txt",snap);
pf=fopen(pauto,"rb"); psz=0;
if(pf){ fseek(pf,0,SEEK_END); psz=ftell(pf); fclose(pf); } }
if(psz>0){ pin=pauto; fprintf(stderr,"[PIN] auto: seeding from %s\n",pauto); }
else { pin=NULL; fprintf(stderr,"[PIN] auto: no .coli_usage or stats.txt in %s yet (no pin this run)\n",snap); }
}
if(pin){
const char *pin_gb=getenv("PIN_GB");
pin_load(&m,pin,pin_gb&&!strcmp(pin_gb,"all")?-1.0:pin_gb?atof(pin_gb):10.0); /* PIN_GB=all (#80) */
}
}
if(getenv("COUPLE")&&*getenv("COUPLE")){ /* coupling-scored cross-layer prefetch (#176) */
g_couple_k=getenv("COUPLE_K")?atoi(getenv("COUPLE_K")):8;
docs/ENVIRONMENT.md
+1 -1
View File
@@ -47,7 +47,7 @@ Format: `VAR` — default — effect.
| `CAP_RAISE` | `1` (on) | Let the engine raise the expert-cache cap above `topk` when RAM allows (bigger batches). `0` fixes the cap. |
| `PREFETCH` | `0` | Prefetch depth for streamed experts. |
| `COLI_MMAP` | `0` | `mmap` the weights instead of read()-ing into slabs. |
| `PIN` | unset | Path to a `.coli_usage` file; pins the hottest experts into a resident "hot store" at startup. |
| `PIN` | unset | Path to a `.coli_usage`/stats file; pins the hottest experts into a resident "hot store" at startup. **`PIN=auto`** seeds from the model dir's live `.coli_usage` (appended after every turn, so each restart's pin placement follows the accumulated real workload) with `stats.txt` as the fallback for a virgin model dir; neither present → no pin this run. |
| `PIN_GB` | `10.0` | Size budget (GB) for the pinned hot store when `PIN` is set. |
| `AUTOPIN` | `1` (on) | Auto-pin the hot store from usage history once ≥5000 selections are recorded. |
| `REPIN` | `0` (off) | Live re-pin the hot store every N emitted tokens (RFC). |