Xin Yang 1f19d8f899 [Perf] Set split_k to 1 for triton_kernels (#30528) ...

Signed-off-by: Xin Yang <xyangx@amazon.com>

2025-12-12 14:07:57 -05:00

..

configs

[Model][Qwen3VL] Tune Triton w8a8 block fp8 kernel for L40s (#29217)

2025-11-21 17:30:55 -08:00

__init__.py

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

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

allspark_utils.py

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

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

bitblas_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

flashinfer_fp4_moe.py

[EPLB] Support EPLB w/ NVFP4 (#29804)

2025-12-11 22:59:40 +00:00

flashinfer_utils.py

[fix] fix SM check for Flashinfer TRTLLM MOE (#30314)

2025-12-12 01:00:58 +00:00

fp8_utils.py

[Bugfix] Fix fp8 DeepGemm compilation issues (#30336)

2025-12-09 20:17:25 -05:00

gptq_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

int8_utils.py

[CI/Build][AMD][Quantization] Fix test_int8_kernel.py by updating int8_utils to use hip.libdevice.round (#30151)

2025-12-05 20:52:11 -08:00

layer_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

machete_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

marlin_utils_fp4.py

[Kernel][Quantization] add w4a8 support for marlin kernel (#24722)

2025-11-29 07:19:33 -08:00

marlin_utils_fp8.py

[Quantization] FP8 Weight Reloading for Quantized RL Rollout (#28480)

2025-12-09 13:54:32 -08:00

marlin_utils_test_24.py

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

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

marlin_utils_test.py

[Kernel][Quantization] add w4a8 support for marlin kernel (#24722)

2025-11-29 07:19:33 -08:00

marlin_utils.py

Fix AWQ MoE marlin check issue in marlin_utils.py for AMD backend (#30102)

2025-12-05 20:54:38 -08:00

mxfp4_utils.py

[Perf] Set split_k to 1 for triton_kernels (#30528)

2025-12-12 14:07:57 -05:00

mxfp6_utils.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

mxfp8_utils.py

[Bugfix] Fix gpt-oss w4a8 DP/EP on B200 (#26729)

2025-10-21 01:51:14 -04:00

nvfp4_emulation_utils.py

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

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

nvfp4_moe_support.py

[MoE] Nvfp4 Masked Gemm: Add flashinfer grouped_gemm_nt_masked (#25990)

2025-11-19 13:29:06 -08:00

ocp_mx_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

petit_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

quant_utils.py

[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691)

2025-12-08 19:29:06 -08:00

w8a8_utils.py

[Quantization] FP8 Weight Reloading for Quantized RL Rollout (#28480)

2025-12-09 13:54:32 -08:00