obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-06-06 00:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Kernel] Batch invariant NVFP4 linear using cutlass (#39912)

Browse Source 
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
Jakub Zakrzewski
2026-05-23 15:41:12 +02:00
committed by GitHub
parent 3f3e862681
commit 5bb8d2767a
5 changed files with 211 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test_areas/misc.yaml
+1
View File
@@ -367,6 +367,7 @@ steps:
- VLLM_TEST_MODEL=deepseek-ai/DeepSeek-V2-Lite-Chat pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle[TRITON_MLA]
- VLLM_TEST_MODEL=Qwen/Qwen3-30B-A3B-Thinking-2507-FP8 pytest -v -s v1/determinism/test_batch_invariance.py::test_v1_generation_is_deterministic_across_batch_sizes_with_needle[FLASH_ATTN]
- pytest -v -s v1/determinism/test_nvfp4_batch_invariant.py
- pytest -v -s v1/determinism/test_nvfp4_batch_invariant_scaled_mm.py
- label: Acceptance Length Test (Large Models) # optional
device: h200_35gb