Xin Yang b1c4f0b265 [Kernel] Optimize grouped topk kernel (#34206) ...

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

2026-02-20 01:34:45 -08:00

..

marlin_moe_wna16

[Bugfix]: Fix display errors in TORCH_CHECK messages (#32942)

2026-01-31 09:48:48 -08:00

permute_unpermute_kernels

[Refactor] Remove align block size logic in moe_permute (#33449)

2026-02-06 10:57:06 -08:00

dynamic_4bit_int_moe_cpu.cpp

[CPU]Parallelize over tokens in int4 moe (#29600)

2025-12-02 06:21:39 +00:00

grouped_topk_kernels.cu

[Kernel] Optimize grouped topk kernel (#34206)

2026-02-20 01:34:45 -08:00

moe_align_sum_kernels.cu

Lora MoE Align Improvements (#29257)

2025-12-09 10:35:16 +08:00

moe_ops.h

[Kernel] Add topk_sigmoid kernel (#31246)

2026-01-21 22:49:51 +00:00

moe_permute_unpermute_op.cu

[Refactor] Remove align block size logic in moe_permute (#33449)

2026-02-06 10:57:06 -08:00

moe_wna16_utils.h

pre-commit autoupdate (#17380)

2025-04-29 06:46:55 -07:00

moe_wna16.cu

[BugFix] Accuracy fix for llama4 int4 - improperly casted scales (#16801)

2025-04-17 22:13:29 -07:00

moeTopKFuncs.cuh

[Kernel] Optimize grouped topk kernel (#34206)

2026-02-20 01:34:45 -08:00

topk_softmax_kernels.cu

[Kernel] Add topk_sigmoid kernel (#31246)

2026-01-21 22:49:51 +00:00

torch_bindings.cpp

[Refactor] Remove align block size logic in moe_permute (#33449)

2026-02-06 10:57:06 -08:00