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

tp = 4, use ep

Browse Source
This commit is contained in:
root
2026-09-03 02:24:32 +00:00
parent d342d8671e
commit 35d63cf0fc
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
computility-run.yaml
View File

@@ -13,7 +13,7 @@ command:
- '0.92' - '0.92'
- --trust-remote-code - --trust-remote-code
- -tp - -tp
- '2' - '4'
- --max-num-seqs - --max-num-seqs
- '2' - '2'
- --disable-log-requests - --disable-log-requests
@@ -35,6 +35,8 @@ command:
env: env:
- name: VLLM_ENGINE_ITERATION_TIMEOUT_S - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
value: 3600 value: 3600
- name: VLLM_ENABLE_EXPERT_PARALLEL
value: 1
- name: BI100_MAX_NUM_SEQS - name: BI100_MAX_NUM_SEQS
value: 2 value: 2
- name: BI100_MOE_COREX_DIRECT_ROUTED - name: BI100_MOE_COREX_DIRECT_ROUTED