Michael Goin c3aea10dc8

[Perf] Use upstream CUTLASS for SM90 Block FP8 kernel (#23280) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

2025-09-11 15:43:14 -07:00

..

attention

[Kernel] Flashinfer MLA (trtllm-gen) decode kernel integration (#21078)

2025-09-10 15:31:10 -07:00

core

[Model] New model support for Motif-1-Tiny (#23414)

2025-09-10 23:29:40 -07:00

mamba

fix some typos (#24616)

2025-09-11 10:48:46 -07:00

moe

[Kernel][B200] mxfp4 fused cutlass moe (#23696)

2025-09-11 17:04:56 -04:00

quantization

[Perf] Use upstream CUTLASS for SM90 Block FP8 kernel (#23280)

2025-09-11 15:43:14 -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

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

quant_utils.py

[Refactor] Remove Duplicate per_block_cast_to_fp8, Remove Dependencies of DeepGEMM (#21787)

2025-08-01 01:13:27 +00:00

test_apply_repetition_penalties.py

[BUG] Fix #20484. Support empty sequence in cuda penalty kernel (#20491)

2025-07-05 19:38:02 -07:00

test_flex_attention.py

Updates to Flex + VLLm integration (#21416)

2025-08-25 09:32:42 -04:00

test_fused_quant_activation.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_onednn.py

[CPU] Refactor CPU unquantized linear (#24150)

2025-09-04 14:28:45 +08:00

test_shuffle_rows.py

[Bugfix] Fix CUDA arch flags for MoE permute (#21426)

2025-07-24 03:23:59 -07:00

test_triton_flash_attention.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

utils.py

[Doc]: fixing typos to improve docs (#24480)

2025-09-08 23:06:04 -07:00