Tyler Michael SmithandClaude Opus 4.6 8cb4e2a378 [Test] Add NVFP4 scale padding contamination test for mm_fp4 ...

Tests whether uninitialized padding rows in NVFP4 swizzled block
scales (from scaled_fp4_quant's torch.empty) can contaminate real
rows' GEMM output via flashinfer mm_fp4.

Key scenarios:
- Poison padding scale rows with NaN
- Poison padding scale rows with max finite values (overflow)
- Poison padding activation rows
- Simulate CUDA graph replay with persistent scale tensor

These target the suspected root cause of NaN in NVFP4 models with
CUDA graphs, where capture sizes (1,2,4,8,...) are not multiples
of 128, leaving uninitialized padding in the swizzled scale layout.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>

2026-03-13 15:00:25 -04:00

..

attention

[MM][OOT] Support CPU seq_lens for OOT MMEncoderAttention kernels (#36605)

2026-03-12 03:28:23 -07:00

core

[torch.compile] Add support for non-contiguous fused RMSNorm + group quant (#36551)

2026-03-11 10:56:55 -07:00

helion

[Kernel][Helion][13/N] Force static_shapes=False in helion register (#36677)

2026-03-12 05:35:29 +00:00

mamba

[CI] Bump mypy version (#34950)

2026-03-04 20:55:11 +00:00

moe

[Test] Fix WorkspaceManager test imports

2026-03-13 14:43:09 -04:00

quantization

Improvements to wvSplitKrc skinny GEMM solution (#34304)

2026-03-10 09:14:27 -07:00

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

allclose_default.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

quant_utils.py

[Perf] Create TMA-aligned input scale tensor for DeepGemm on Hopper (#32619)

2026-01-22 15:47:04 -05:00

test_apply_repetition_penalties.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

test_cache_kernels.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

test_concat_mla_q.py

[Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA query concat - DeepSeek-V3.2 (#34917)

2026-03-09 09:50:36 -07:00

test_cp_gather_fp8.py

[Attention][Perf] Optimize cp_gather_and_upconvert_fp8_kv_cache - DeepSeek-v3.2 (#35290)

2026-03-09 09:46:57 -07:00

test_fla_layernorm_guard.py

[Bugfix] Fix dtype mismatch in RMSNormGated.forward_native() during torch.compile (#35256)

2026-03-01 15:14:46 -05:00

test_flex_attention.py

[Tests] Standardize RNG seed utility across test files (#32982)

2026-01-24 06:47:14 +00:00

test_fused_quant_activation.py

[Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747)

2026-01-08 15:20:49 -08:00

test_fused_recurrent_packed_decode.py

[Perf] add packed recurrent fast path for decode (#36596)

2026-03-12 04:01:57 -07:00

test_fused_sigmoid_gating_delta_rule.py

[Kernel] Add fused_sigmoid_gating_delta_rule_update kernel for Qwen3 Next (#35777)

2026-03-08 23:41:01 -07:00

test_nvfp4_scale_padding_contamination.py

[Test] Add NVFP4 scale padding contamination test for mm_fp4

2026-03-13 15:00:25 -04:00

test_onednn.py

[CPU] Refactor CPU attention backend (#27954)

2025-11-12 09:43:06 +08:00

test_shuffle_rows.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_top_k_per_row.py

[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

2026-03-05 10:36:39 +00:00

utils.py

[Refactor] Replace activation: str with MoEActivation enum (#33843)

2026-02-11 17:29:32 -08:00