3 people 7b03584de8 Silu v2 (#25074) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: elvircrn <elvircrn@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>

2025-10-10 15:19:53 +00:00

..

configs

[deepseek] add EP8 FusedMOE config for H200 and B200 (#26331)

2025-10-07 10:38:54 -07:00

__init__.py

[Model] Apply shared experts overlap optimization to all models with shared experts (#26145)

2025-10-09 11:31:04 -04:00

batched_deep_gemm_moe.py

Silu v2 (#25074)

2025-10-10 15:19:53 +00:00

batched_triton_or_deep_gemm_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

config.py

[Feature][OCP MX] Support mxfp6 and mixed mxfp6-mxfp4 (#21166)

2025-10-07 09:35:26 -04:00

cpu_fused_moe.py

Add SwigluOAI implementation for CPUFusedMOE (#26347)

2025-10-07 20:17:49 -06:00

cutlass_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

deep_gemm_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

deep_gemm_utils.py

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

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

deepep_ht_prepare_finalize.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

deepep_ll_prepare_finalize.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

flashinfer_cutlass_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

flashinfer_cutlass_prepare_finalize.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

flashinfer_trtllm_moe.py

Fix per file ruff ignores related to typing (#26254)

2025-10-05 16:37:55 +00:00

fused_batched_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

fused_marlin_moe.py

[Bugfix] Disable moe inplace for torch >= 2.9 (#26497)

2025-10-09 18:07:38 +00:00

fused_moe.py

[Bugfix] Disable moe inplace for torch >= 2.9 (#26497)

2025-10-09 18:07:38 +00:00

gpt_oss_triton_kernels_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

layer.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

modular_kernel.py

[Bug] Fix modular_kernel: ZeroDivisionError: integer division or modulo by zero (#26528)

2025-10-09 15:13:27 -07:00

moe_align_block_size.py

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

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

moe_pallas.py

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

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

moe_permute_unpermute.py

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

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

moe_torch_iterative.py

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

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

pplx_prepare_finalize.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

prepare_finalize.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

rocm_aiter_fused_moe.py

Fix per file ruff ignores related to simplification (#26259)

2025-10-05 20:31:53 +00:00

routing_simulator.py

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

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

shared_fused_moe.py

[Model] Apply shared experts overlap optimization to all models with shared experts (#26145)

2025-10-09 11:31:04 -04:00

topk_weight_and_reduce.py

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

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

triton_deep_gemm_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

trtllm_moe.py

[Kernels] Modular kernel refactor (#24812)

2025-10-08 17:51:52 -04:00

utils.py

[Bugfix] Disable moe inplace for torch >= 2.9 (#26497)

2025-10-09 18:07:38 +00:00