xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-16 14:17:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Add Blackwell LM Eval Small Models test to nightly (#26052)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-10-05 16:59:50 -04:00 committed by GitHub
parent b893d661b1
commit 60bc25e74c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 16 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
.buildkite/test-pipeline.yaml
View File

@ -835,11 +835,11 @@ steps:
- pytest -v -s tests/kernels/moe/test_flashinfer.py - pytest -v -s tests/kernels/moe/test_flashinfer.py
- pytest -v -s tests/compile/test_silu_mul_quant_fusion.py - pytest -v -s tests/compile/test_silu_mul_quant_fusion.py
- label: GPT-OSS Eval (Blackwell) - label: Blackwell GPT-OSS Eval
timeout_in_minutes: 60 timeout_in_minutes: 60
working_dir: "/vllm-workspace/" working_dir: "/vllm-workspace/"
gpu: b200 gpu: b200
optional: true # disable while debugging optional: true # run on nightlies
source_file_dependencies: source_file_dependencies:
- tests/evals/gpt_oss - tests/evals/gpt_oss
- vllm/model_executor/models/gpt_oss.py - vllm/model_executor/models/gpt_oss.py
@ -866,6 +866,16 @@ steps:
commands: commands:
- pytest -s -v tests/quantization/test_blackwell_moe.py - pytest -s -v tests/quantization/test_blackwell_moe.py
- label: Blackwell LM Eval Small Models
timeout_in_minutes: 75
gpu: b200
optional: true # run on nightlies
source_file_dependencies:
- csrc/
- vllm/model_executor/layers/quantization
commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt --tp-size=1
##### 1 GPU test ##### ##### 1 GPU test #####
##### multi gpus test ##### ##### multi gpus test #####

4
tests/evals/gsm8k/configs/models-blackwell.txt Normal file
View File

@ -0,0 +1,4 @@
Qwen3-0.6B-FP8.yaml
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
Qwen1.5-MoE-W4A16-CT.yaml
DeepSeek-V2-Lite-Instruct-FP8.yaml