[CI] Raise gsm8k startup timeout for Qwen3 NVFP4 trtllm configs (#46881)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Kevin H. Luu
2026-06-26 16:15:00 -07:00
committed by GitHub
co-authored by Claude
parent 6d37570a1c
commit cfe8a4d063
2 changed files with 2 additions and 0 deletions
@@ -2,4 +2,5 @@ model_name: "nvidia/Qwen3-30B-A3B-FP4"
accuracy_threshold: 0.89
num_questions: 1319
num_fewshot: 5
startup_max_wait_seconds: 1200
server_args: "--enforce-eager --max-model-len 4096"
@@ -2,6 +2,7 @@ model_name: "nm-testing/Qwen3-Next-80B-A3B-Instruct-NVFP4"
accuracy_threshold: 0.75
num_questions: 1319
num_fewshot: 5
startup_max_wait_seconds: 1200
server_args: >-
--enforce-eager
--max-model-len 4096