tonyliu312 6cc8577421 [Kernel] Marlin MoE: include SM 12.x in default arch list (#40923) ...

Signed-off-by: Tony Liu <tonyliu0512@gmail.com>
Co-authored-by: Tony Liu <tonyliu0512@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>

2026-05-28 15:30:26 +08:00

..

.gitignore

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

awq_marlin_repack.cu

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

dequant.h

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

generate_kernels.py

[Bugfix] Fix SM121 (DGX Spark) exclusion from Marlin/CUTLASS FP8 paths (#35568)

2026-05-15 10:59:00 -07:00

gptq_marlin_repack.cu

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

kernel.h

[Bugfix]fix output Nan/Inf in marlin if dtype=float16 (#33972)

2026-03-27 16:36:08 -07:00

marlin_dtypes.cuh

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

marlin_int4_fp8_preprocess.cu

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

marlin_mma.h

[Refactor] Rename gptq_marlin to marlin to match MoE (#32952)

2026-01-23 16:48:12 -05:00

marlin_template.h

[Kernel] Add MXFP8 to Marlin GEMM/MoE and refactor Mxfp8LinearOp (#34664)

2026-04-01 09:41:42 -07:00

marlin.cu

[Kernel] Marlin MoE: include SM 12.x in default arch list (#40923)

2026-05-28 15:30:26 +08:00

marlin.cuh

[5/n] Migrate CUTLASS MLA, hadamard, awq, allspark and DSV3 fused a gemm to torch stable ABI (continued) (#42339)

2026-05-13 07:24:39 +00:00