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

bench: pass the resolved GLM engine path to eval_glm.py — cwd-relative ./glm default broke coli bench from other dirs (#203)

Browse Source 
cmd_bench builds the eval_glm.py command but did not pass --glm,
so eval_glm.py fell back to ./glm which breaks when running from
any directory other than the source tree. Pass the already-resolved
GLM variable via --glm, matching --data and --snap.

Assisted-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benny Powers
2026-07-14 19:55:36 +03:00
committed by GitHub
parent e21318e678
commit ab09dc52f3
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/coli
+1 -1
View File
@@ -585,7 +585,7 @@ def cmd_bench(a):
print(f" {C.dim}downloading missing datasets: {', '.join(missing)}{C.r}") print(f" {C.dim}downloading missing datasets: {', '.join(missing)}{C.r}")
subprocess.call([py, os.path.join(TOOLS,"fetch_benchmarks.py"), subprocess.call([py, os.path.join(TOOLS,"fetch_benchmarks.py"),
"--out", a.data, "--tasks", ",".join(missing), "--limit", str(max(a.limit,200))]) "--out", a.data, "--tasks", ",".join(missing), "--limit", str(max(a.limit,200))])
cmd=[py, os.path.join(TOOLS,"eval_glm.py"), "--snap",a.model, cmd=[py, os.path.join(TOOLS,"eval_glm.py"), "--glm", GLM, "--snap",a.model,
"--tasks", tasks, "--limit", str(a.limit), "--data", a.data] "--tasks", tasks, "--limit", str(a.limit), "--data", a.data]
if a.ram: cmd+=["--ram",str(a.ram)] if a.ram: cmd+=["--ram",str(a.ram)]
e=env_for(a) e=env_for(a)