XuruiYang 845adb3ec6

[Model] Add LongCat-Flash (#23991) ...

Signed-off-by: yangxurui <yangxurui@meituan.com>
Co-authored-by: yangxurui <yangxurui@meituan.com>

2025-09-24 21:53:40 -07:00

..

marlin_moe_wna16

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

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

permute_unpermute_kernels

Fix CUDA permute/unpermute for use with DeepGemm Moe (#17934)

2025-07-27 07:08:00 -07:00

dynamic_4bit_int_moe_cpu.cpp

[fix]: add Arm 4bit fused moe support (#23809)

2025-09-24 01:32:22 +00:00

grouped_topk_kernels.cu

Use macro guard CUDA functions for back compatibility in grouped_topk_kernel.cu (#25346)

2025-09-23 09:45:39 -07:00

moe_align_sum_kernels.cu

[Model] Add LongCat-Flash (#23991)

2025-09-24 21:53:40 -07:00

moe_ops.h

[Kernel] Add fused grouped_topk kernel for MoE (#23274)

2025-08-25 11:47:52 -07:00

moe_permute_unpermute_op.cu

[Kernel] CUTLASS MoE FP8: Integrate cuda moe permute/unpermute (#23045)

2025-08-20 10:35:26 -04:00

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

topk_softmax_kernels.cu

Apply fixes for CUDA 13 (#24599)

2025-09-17 09:15:42 -04:00

torch_bindings.cpp

[Kernel] Add fused grouped_topk kernel for MoE (#23274)

2025-08-25 11:47:52 -07:00