nvjullin f66673a39d

[Kernel] Added flashinfer fp8 per-tensor gemms (#22895) ...

Signed-off-by: Julien Lin <jullin@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2025-08-26 06:54:04 -07:00

..

attention

[NVIDIA][torch.compile] Support Flashinfer TRTLLM FP8-q/kv NVFP4-out Attention Kernel (#22703)

2025-08-22 22:09:05 +00:00

core

[Kernel] Add cuda kernel for gpt_oss activation (#22951)

2025-08-17 05:03:24 +00:00

mamba

[Mamba] - refactor: Renamed mamba_attn to mamba2_attn (#22818)

2025-08-15 06:38:05 +00:00

moe

[CI Fix] Pin deepep and pplx tags in tools/ep_kernels/, gate multigpu tests (#23568)

2025-08-25 18:29:00 -07:00

quantization

[Kernel] Added flashinfer fp8 per-tensor gemms (#22895)

2025-08-26 06:54:04 -07:00

__init__.py

…

allclose_default.py

…

quant_utils.py

…

test_apply_repetition_penalties.py

…

test_cutlass_mla_decode.py

…

test_flex_attention.py

Updates to Flex + VLLm integration (#21416)

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

test_fused_quant_activation.py

…

test_onednn.py

[CPU] Refactor CPU W8A8 scaled_mm (#23071)

2025-08-21 09:34:24 +08:00

test_shuffle_rows.py

…

test_triton_flash_attention.py

…

utils.py

[Kernel] [Quantization] Add MXFP4 and bias support for marlin kernel (#22428)

2025-08-14 11:23:22 -07:00