karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity

[CI] Increase Qwen3.5 MTP GSM8K generation length (#49881)

Browse Source 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Jiangyun Zhu
2026-07-28 18:04:36 +08:00
committed by GitHub
co-authored by OpenAI Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 247470f23a
commit 25ace8fe5d
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/evals/gsm8k/configs/Qwen3.5-397B-A17B-NVFP4-DEP2-MTP.yaml
+2 -1
View File
@@ -3,8 +3,9 @@ accuracy_threshold: 0.88
tolerance: 0.03
num_questions: 1319
num_fewshot: 5
max_tokens: 12000
server_args: >-
--max-model-len 4096
--max-model-len 16384
--data-parallel-size 2
--enable-expert-parallel
--max-num-seqs 384