Wentao YeandGitHub dad95e34d8 [Feature] Support batch invariant rms norm with residual (#42453) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2026-06-03 15:22:01 -04:00

..

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

expose flex block size for batch invariant mode (#41252)

2026-05-13 14:11:57 -07:00

test_cutlass_batch_invariance.py

[Perf] Batch invariance with Cutlass fp8 support, 28.9% E2E latency improvement (#40408)

2026-05-11 12:20:58 -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_scaled_mm.py

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

2026-05-23 09:41:12 -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

[Feature] Support batch invariant rms norm with residual (#42453)

2026-06-03 15:22:01 -04:00

utils.py

uncomment flex backend for batch invariant mode (#40842)

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