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

Merge pull request #232 from nbeerbower/profiling-upstream

Browse Source 
Profiling: PROF=1 opt-in performance profile + live per-turn Profiling page in the web dashboard
This commit is contained in:
Vincenzo
2026-07-16 19:58:31 +02:00
committed by GitHub
parent 98f7c88ca9 36394bc317
commit ee5d273cd4
11 changed files with 518 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/ENVIRONMENT.md
+1
View File
@@ -63,6 +63,7 @@ Format: `VAR` — default — effect.
| `ABSORB` | `-1` (auto: absorbed for S≤4) | MLA attention absorption mode. |
| `IDOT` | `1` | Integer dot-product kernel. `IDOT=0` uses exact f32 kernels (for A/B numerical checks). |
| `COLI_POLICY` | `quality` | Resource policy: `quality`, `balanced`, or `experimental-fast`. |
| `PROF` | `0` (off) | Performance profile: a startup header (machine + effective config), then per run — or per turn in serve mode, on stderr — forward-latency percentiles (p50/p90/p99/max), expert-I/O totals and cache-tier fill, phase shares of wall time, and a verdict naming the knob most likely to help on this machine. Output is additive; `PROF` unset changes nothing. |
---