xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-09 12:22:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Temporary fix to LM Eval Small Models (#28324)

Browse Source 
Signed-off-by: zhewenli <zhewenli@meta.com>
This commit is contained in:
Zhewen Li 2025-11-09 13:08:38 -08:00 committed by GitHub
parent 4a8d6bd168
commit a65a934ebe
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/evals/gsm8k/configs/Qwen1.5-MoE-W4A16-CT.yaml
View File

@ -3,3 +3,6 @@ accuracy_threshold: 0.45
num_questions: 1319 num_questions: 1319
num_fewshot: 5 num_fewshot: 5
max_model_len: 4096 max_model_len: 4096
# Duo stream incompatabilbe with this model: https://github.com/vllm-project/vllm/issues/28220
env:
VLLM_DISABLE_SHARED_EXPERTS_STREAM: "1"

4
tests/evals/gsm8k/test_gsm8k_correctness.py
View File

@ -62,9 +62,11 @@ def test_gsm8k_correctness_param(config_filename, tp_size):
str(tp_size), str(tp_size),
] ]
env_dict = eval_config.get("env", None)
# Launch server and run evaluation # Launch server and run evaluation
with RemoteOpenAIServer( with RemoteOpenAIServer(
eval_config["model_name"], server_args, max_wait_seconds=480 eval_config["model_name"], server_args, env_dict=env_dict, max_wait_seconds=480
) as remote_server: ) as remote_server:
server_url = remote_server.url_for("v1") server_url = remote_server.url_for("v1")