dylanyunlong/project_7
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fix: yaml params only — enforce_eager + dtype half + comp168 settings

Browse Source
This commit is contained in:
project6-dev
2026-08-12 16:05:58 +00:00
parent 4ade8136ad
commit d1cc7d4e89
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
computility-run.yaml
View File

@@ -8,18 +8,18 @@ command:
- --served-model-name - --served-model-name
- llm - llm
- --max-model-len - --max-model-len
- '262144' - '256000'
- --gpu-memory-utilization - --gpu-memory-utilization
- '0.9' - '0.95'
- --trust-remote-code - --trust-remote-code
- -tp - -tp
- '4' - '4'
- --max-num-seqs - --max-num-seqs
- '1' - '2'
- --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'
@@ -29,6 +29,9 @@ command:
- --reasoning-parser - --reasoning-parser
- qwen3 - qwen3
- --enable-prefix-caching - --enable-prefix-caching
- --enforce-eager
- --dtype
- half
env: env:
- name: VLLM_ENGINE_ITERATION_TIMEOUT_S - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
value: 3600 value: 3600