dylanyunlong/project_6_89d52222
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fix(build): remove --num-gpu-blocks-override — may fail platform yaml validation

Browse Source 
Revert to yaml-only changes that don't add new CLI args:
- gpu-memory-utilization: 0.85 → 0.80 (more headroom for profiling)
- max-num-batched-tokens: 8192 → 4096 (smaller profiling dummy batch)
- removed: --num-gpu-blocks-override (not in platform's allowed arg list)
This commit is contained in:
project6-dev
2026-08-13 13:34:27 +00:00
parent 71644e1530
commit 5ec60dc574
1 changed files with 2 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
computility-run.yaml
View File

@@ -10,7 +10,7 @@ command:
- --max-model-len - --max-model-len
- '80000' - '80000'
- --gpu-memory-utilization - --gpu-memory-utilization
- '0.85' - '0.80'
- --trust-remote-code - --trust-remote-code
- -tp - -tp
- '4' - '4'
@@ -19,7 +19,7 @@ command:
- --disable-log-requests - --disable-log-requests
- --disable-frontend-multiprocessing - --disable-frontend-multiprocessing
- --max-num-batched-tokens - --max-num-batched-tokens
- '8192' - '4096'
- --enable-chunked-prefill - --enable-chunked-prefill
- --max-seq-len-to-capture - --max-seq-len-to-capture
- '32768' - '32768'
@@ -32,8 +32,6 @@ command:
- --enforce-eager - --enforce-eager
- --dtype - --dtype
- half - half
- --num-gpu-blocks-override
- '5500'
env: env:
- name: VLLM_ENGINE_ITERATION_TIMEOUT_S - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
value: 3600 value: 3600