Qi Yuhang 0f04a5f428 Optimize cutlass int8 gemm kernel for large M on SM89 Ada GPU (#10714)

2025-09-21 17:04:27 -07:00

..

allreduce

…

attention

Disable kernel cutlass_mla_decode on SM103 (#10058)

2025-09-06 01:35:18 -07:00

cpu

[CPU] Add gelu_and_mul kernel in sgl-kernel and add ut (#9300)

2025-09-08 23:23:13 -07:00

cutlass_extensions

Update CUTLASS. Refine KernelSchedule for fp8 (grouped) gemm. (#10491)

2025-09-16 02:47:37 -07:00

elementwise

[1/2] Speed up trtllm_mla attention backend (>10% e2e) (#10473)

2025-09-15 11:53:21 -07:00

gemm

Optimize cutlass int8 gemm kernel for large M on SM89 Ada GPU (#10714)

2025-09-21 17:04:27 -07:00

grammar

…

kvcacheio

Page first direct IO kernel (#10060)

2025-09-10 13:35:34 +08:00

mamba

Add mamba kernel (#10234)

2025-09-09 12:58:43 -07:00

memory

…

moe

[sgl-kernel] Support moe_sum_reduce cuda kernel (#10321)

2025-09-19 14:12:09 +08:00

spatial

…

speculative

[Feature] Speculative decoding support lookahead (#9873)

2025-09-18 16:42:41 -07:00

common_extension_rocm.cc

Fix errors of hicache kernels in sgl-kernel for ROCm (#10339)

2025-09-11 14:54:34 -07:00

common_extension.cc

[sgl-kernel] Support moe_sum_reduce cuda kernel (#10321)

2025-09-19 14:12:09 +08:00

flash_extension.cc

…

spatial_extension.cc

…