liangel-02andGitHub 7fd05e05ae uncomment flex backend for batch invariant mode (#40842) ...

Signed-off-by: Angel Li <liangel@meta.com>

2026-04-28 21:05:14 -07:00

..

conftest.py

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007)

2026-03-23 18:31:14 -04:00

test_batch_invariance.py

[Startup][UX] Enable CUDAGraph memory profiling by default (#38284)

2026-04-21 18:16:59 -04:00

test_matmul_batch_invariant.py

Added general ND x ND matmul and unit test for it (#39909)

2026-04-18 10:05:21 -04:00

test_nvfp4_batch_invariant.py

[Feature] Batch invariant nvfp4 linear support (#39322)

2026-04-08 16:29:13 -04:00

test_online_batch_invariance.py

[Test] Only Run MLA model when user explicitly set for batch invariance (#37719)

2026-03-22 09:09:12 -04:00

test_rms_norm_batch_invariant.py

[Perf] Optimize batch invariant with fused rms norm, 2.1% E2E latency improvement (#40413)

2026-04-21 19:51:03 +00:00

utils.py

uncomment flex backend for batch invariant mode (#40842)

2026-04-28 21:05:14 -07:00