dylanyunlong/project_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fix yaml

Browse Source
This commit is contained in:
root
2026-09-02 02:44:22 +00:00
parent 27878c8689
commit 7f16b711a7
1 changed files with 38 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
computility-run.yaml
View File

@@ -1,48 +1,53 @@
concurrency: 1
command:
- bash
- -c
- >-
python3 /workspace/qwen3_6_scripts/patch_chat_template.py /model 2>&1 || echo '[runtime] chat template patch failed';
exec python3 -m vllm.entrypoints.openai.api_server
--model /model
--served-model-name llm
--max-model-len 131072
--gpu-memory-utilization 0.92
--trust-remote-code
-tp 4
--max-num-seqs 2
--disable-log-requests
--disable-frontend-multiprocessing
--max-num-batched-tokens 4096
--enable-chunked-prefill
--max-seq-len-to-capture 32768
--enable-auto-tool-choice
--tool-call-parser qwen3_coder
--reasoning-parser qwen3
--enable-prefix-caching
--enforce-eager
--dtype half
- python3
- -m
- vllm.entrypoints.openai.api_server
- --model
- /model
- --served-model-name
- llm
- --max-model-len
- '131072'
- --gpu-memory-utilization
- '0.92'
- --trust-remote-code
- -tp
- '4'
- --max-num-seqs
- '2'
- --disable-log-requests
- --disable-frontend-multiprocessing
- --max-num-batched-tokens
- '4096'
- --enable-chunked-prefill
- --max-seq-len-to-capture
- '32768'
- --enable-auto-tool-choice
- --tool-call-parser
- qwen3_coder
- --reasoning-parser
- qwen3
- --enable-prefix-caching
- --enforce-eager
- --dtype
- half
env:
- name: VLLM_ENGINE_ITERATION_TIMEOUT_S
value: '3600'
value: 3600
- name: BI100_MAX_NUM_SEQS
value: '2'
# --- MoE kernel selection ---
value: 2
- name: BI100_MOE_COREX_DIRECT_ROUTED
value: '1'
value: 1
- name: BI100_MOE_COREX_TOPK_SOFTMAX
value: '1'
# --- GDN kernel selection ---
value: 1
- name: BI100_GDN_COREX_PACKED_DECODE
value: '1'
# --- Hybrid KV/GDN cache ---
value: 1
- name: BI100_HYBRID_KV_ACCOUNTING
value: full_attention
- name: BI100_GDN_CACHE_POLICY
value: admission64
- name: BI100_GDN_RESTORE_MODE
value: hybrid64
# --- Image fetch timeout (container network) ---
- name: VLLM_IMAGE_FETCH_TIMEOUT
value: '10'
value: 10