yewentao256 e20a7be4d0 optimize per token group quant ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2026-05-19 20:13:19 +00:00

..

awq

[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

cutlass_w4a8

[4/n] Migrate FP4/W4A8 CUTLASS kernels to torch stable ABI (#37503)

2026-03-31 10:21:13 -07:00

fp4

[Perf] Padded nvfp4 quant kernel to remove additional copy, 2.4%~5.7% e2e performance improvement (#42774)

2026-05-18 16:38:12 -07:00

gptq_allspark

[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

hadamard/hadacore

[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

w8a8

optimize per token group quant

2026-05-19 20:13:19 +00:00

vectorization_utils.cuh

[2/n] Migrate per_token_group_quant to torch stable ABI (#36058)

2026-03-25 10:15:13 -07:00

vectorization.cuh

[2/n] Migrate per_token_group_quant to torch stable ABI (#36058)

2026-03-25 10:15:13 -07:00