Qi Yuhang ce112c07fe [sgl-kernel][4/N]Support Expert Specialization Grouped GEMM (#12080)

2025-10-27 01:20:01 -07:00

..

allreduce

…

attention

…

cpu

[CPU] Optimize FP16 decode_attention_cpu (#10652)

2025-10-22 21:39:51 -07:00

cutlass_extensions

[Bug] Fix Issue#10215 (#10572)

2025-09-25 09:51:50 +08:00

elementwise

[DeepseekV32] Add fast_topk_transform_ragged_fused kernel (#11815)

2025-10-19 17:13:39 -07:00

expert_specialization

[sgl-kernel][4/N]Support Expert Specialization Grouped GEMM (#12080)

2025-10-27 01:20:01 -07:00

gemm

[sgl-kernel] feat: Support sm120 cutlass fp8 gemm kernel (#9403)

2025-10-26 23:45:45 -07:00

grammar

…

kvcacheio

[HiCache]Page head layout IO kernel (#11615)

2025-10-26 15:53:50 +08:00

mamba

…

memory

…

moe

[2/N]Support DeepSeek-R1 w4a8 low latency deepep (#8464)

2025-10-24 17:41:16 -07:00

quantization/gguf

[7/n] decouple quantization impl from vllm dependency - gguf kernel (#11019)

2025-10-11 14:04:57 -07:00

spatial

…

speculative

[speculative decoding] rename lookahead to ngram (#11010)

2025-09-28 21:06:59 -07:00

common_extension_rocm.cc

…

common_extension.cc

[HiCache]Page head layout IO kernel (#11615)

2025-10-26 15:53:50 +08:00

flash_extension.cc

[NVIDIA] FA3/FA4 Fix (#11606)

2025-10-19 17:10:10 -07:00

flashmla_extension.cc

[sgl-kernel] support flashmla libtorch (#11717)

2025-10-21 21:17:50 -07:00

spatial_extension.cc

…