frozenleaves/vllm-ascend
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm-ascend.git synced 2025-10-20 13:43:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update omni_infer_server_template_a3_ds.yml (#3303)

Browse Source 
update doc
This commit is contained in:
zhenwenqi2024
2025-09-30 18:40:56 +08:00
committed by GitHub
parent 657f065f42
commit 9dd8621212
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/omni_infer_server_template_a3_ds.yml
View File

@ -180,7 +180,7 @@
export PYTORCH_NPU_ALLOC_CONF="expandable_segments:True"
prefill_server_list=$(echo "$PREFILL_SERVER_LIST" | awk '$1=$1' | tr -d ',')
KV_PARALLEL_SIZE=$((PREFILL_POD_NUM + 1))
MODEL_EXTRA_CFG_PATH="/workspace/omniinfer/tests/test_config/test_config_prefill.json"
MODEL_EXTRA_CFG_PATH="/workspace/omniinfer/tests/test_config/test_config_prefill_bf16.json"
EXTRA_ARGS='--max-num-batched-tokens 66560 --enforce-eager --no-enable-prefix-caching --enable-expert-parallel --disable-log-requests --max-num-seqs 16'
GPU_UTIL=0.93
VLLM_ENABLE_MC2=1