Xiaoyu Zhang fb04d43428 [kimi k2 thinking] Avoid useless torch.zeros_ (#13596) ...

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

2025-11-21 13:15:27 +08:00

..

quantization

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

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

testing

Fix FusedSetKVBufferArg in RotaryEmbedding (#11003)

2025-09-28 11:17:27 -07:00

__init__.py

[kimi k2 thinking] Avoid useless torch.zeros_ (#13596)

2025-11-21 13:15:27 +08:00

_fa4_interface.py

Add env var to disable FA4 warmup (#12430)

2025-10-31 12:25:00 -07:00

allreduce.py

[Feature] Integrate quick allreduce and select the best allreduce implementation (#6619)

2025-07-24 20:48:42 -07:00

attention.py

[fix] fix cutlass_mla_backend with cuda_graph and add sm_scale for sgl-kernel cutlass_mla (#7184)

2025-06-14 12:45:41 -07:00

cutlass_moe.py

[1/n]: add cutlass W4A8 moe kernel for hopper architecture (#7772)

2025-07-04 20:50:12 -07:00

elementwise.py

Super tiny add UT for copy_to_gpu_no_ce (#12270)

2025-11-04 09:40:51 +08:00

expert_specialization.py

[sgl-kernel][3/N]Support Expert Specialization Grouped GEMM (#11674)

2025-10-15 13:39:31 -07:00

flash_attn.py

[NVIDIA] FA3/FA4 Fix (#11606)

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

flash_mla.py

[sgl-kernel] support custom fp8 flashmla kernel (#13087)

2025-11-13 12:45:21 -08:00

fused_moe.py

[kimi k2 thinking] Avoid useless torch.zeros_ (#13596)

2025-11-21 13:15:27 +08:00

gemm.py

move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

grammar.py

fix sgl-kernel unit tests (#5666)

2025-04-23 01:18:30 -07:00

hadamard.py

[sgl-kernel] support hadamard (#11663)

2025-10-15 19:00:44 -07:00

kvcacheio.py

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

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

load_utils.py

Clean up sgl kernel (#12413)

2025-10-31 01:13:34 -07:00

mamba.py

Add mamba kernel (#10234)

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

marlin.py

[2/n]decouple quantization implementation from vLLM dependency (#8112)

2025-08-14 03:19:03 -07:00

memory.py

[1 / 2] register weak_ref_tensor in sgl-kernel (#12999)

2025-11-10 22:12:59 +08:00

moe.py

Support moe topk sigmoid kernel (#13049)

2025-11-20 00:24:37 +08:00

sampling.py

Minor style fixes for sgl-kernel (#9289)

2025-08-18 09:38:35 -07:00

scalar_type.py

refactor: Move scalar_types.py to sgl-kernel to avoid circular import (#8720)

2025-08-07 19:22:16 -07:00

sparse_flash_attn.py

[Feat] QWen-1M context support[1/2]: Update block sparse attention backend utils kernel (#5847)

2025-04-28 11:03:17 -07:00

spatial.py

Optional extension for green context (#9231)

2025-08-15 21:33:52 +08:00

speculative.py

move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

test_utils.py

Reland [1/2] Optimizations and refactors about quant kernel (#10312)

2025-10-11 15:59:03 +08:00

top_k.py

[sgl-kernel][Deepseek V3.2] Add row_starts to topk kernel (#12582)

2025-11-07 18:33:27 -08:00

utils.py

move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

version.py

chore: bump sgl-kernel version to 0.3.17.post2 (#13542)

2025-11-18 22:08:23 -08:00