Wentao Ye 0d453e2336 [Perf] Batch invariance with Cutlass fp8 support, 28.9% E2E latency improvement (#40408) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

2026-05-11 12:20:58 -04:00

..

cutlass_w4a8

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

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

fp4

[Bugfix][Kernel] nvfp4 cutlass MoE: fix nvfp4 experts quant out-of-bounds read for expert counts not divisible by 4 or 16 (#40351)

2026-04-21 19:06:09 +00:00

w8a8

[Perf] Batch invariance with Cutlass fp8 support, 28.9% E2E latency improvement (#40408)

2026-05-11 12:20:58 -04:00

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