minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
11,783 Commits 3 Branches 0 Tags
a2d30d27fe855f52c5356b254c1960cc52a4c715
Commit Graph
30 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
hlu1 9457c049e1 [Qwen3.5] Enable MTP spec_v2 and add test for nvidia/Qwen3.5-397B-A17B-NVFP4 (#19391) 2026-03-04 14:01:25 -08:00
hlu1 468e3dc56b [Qwen3.5] Set full attn_backend to trtllm_mha on SM100 by default when possible (#19030) 2026-03-02 23:14:53 +08:00
hlu1 bba2fc49a1 [Qwen3.5] Enable nvfp4 checkpoint (#18937) 2026-02-19 12:24:05 +08:00
hlu1 4637970dfb [Qwen3Next] Optimize fused_sigmoid_gating_delta_rule_update_kernel (#18271) 2026-02-07 11:59:42 +08:00
hlu1 0e86de7c0b Remove deepseek-r1 from THINKING_MODE_CHOICES in run_eval.py (#17178) 2026-01-15 16:53:06 -08:00
hlu1 aeb480c11f Add top-p to run_eval.py (#16844) 2026-01-10 17:10:37 +08:00
hlu1 12a0292bfd Revert "[sgl-kernel] Update flashmla to include fp8 sparse_mla optimizations" (#16678) 2026-01-08 10:23:06 +08:00
hlu1 930705863f [sgl-kernel] Update flashmla to include fp8 sparse_mla optimizations (#15242) 2025-12-16 15:12:19 -08:00
hlu1 618ca23802 [Deepseek] Refactor deepseek server_args _handle_model_specific_adjustments (#13687) 2025-11-23 12:41:14 -08:00
hlu1 7291c72e57 [Deepseek V3.2] Change indexer weights_proj to fp32 (#13459) 2025-11-20 12:24:10 -08:00
hlu1 a8fcbf6fe3 [Deepseek V3.2] Use torch.compile to speed up torch.cat in nsa (#13022) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-11-17 12:20:49 -08:00
hlu1 a7002e614b [Deepseek V3.2] Clean up MTP (#13236) 2025-11-14 11:01:37 -08:00
hlu1 0d4a418424 [Deepseek V3.2] Fix accuracy bug in the Indexer (#12583) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-11-11 16:15:26 -08:00
hlu1 b8ddc296f4 [sgl-kernel][Deepseek V3.2] Add row_starts to topk kernel (#12582) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-11-07 18:33:27 -08:00
hlu1 bef37d6de8 [Deepseek V3.2] Only skip Indexer logits computation when is_extend_without_speculative (#12816) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-11-07 01:34:04 -08:00
hlu1 42e1a72efb [Deepseek V3.2] Enable flashmla_auto with MTP (#12294) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-10-28 23:51:20 -07:00
hlu1 0ee831dee0 Update deepseek_v32.md (#12296) 2025-10-28 14:52:38 -07:00
hlu1 81a632ace6 [DeepseekV32] Enable flashmla_prefill kernel with fp8 kvcache (#11655) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-10-27 23:11:48 -07:00
hlu1 3b80232d06 [DeepseekV32] Add fast_topk_transform_ragged_fused kernel (#11815) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-10-19 17:13:39 -07:00
hlu1 d6777a706d Add --thinking-mode to run_eval (#11189) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-10-03 16:49:39 +08:00
hlu1 592ddf374f Add simple docker file for B300 (#10944) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-09-26 17:26:57 -07:00
hlu1 5f1eb20484 [chore] Remove unused ep_moe cuda kernels (#9956) 2025-09-06 01:35:50 -07:00
hlu1 039cef76aa Remove non-accelerated targets(100 and up) from cmake (#10041) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-09-06 01:35:28 -07:00
hlu1 4c22ebe2e8 Disable kernel cutlass_mla_decode on SM103 (#10058) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-09-06 01:35:18 -07:00
hlu1 2985090084 Update flashinfer to 0.3.1 for B300 support (#10087) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-09-05 13:41:01 -07:00
hlu1 1e85589dc5 Make fp4_quantize kernels work on sm103 (#9807) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-08-29 21:15:08 -07:00
hlu1 7a16db9bd9 Make sm100 fp8 kernels available on sm103 (#9789) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-08-28 23:47:29 -07:00
hlu1 a7d825fccc Skip some tests on Blackwell (#9777) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-08-28 20:00:32 -07:00
hlu1 ccd3fb946e [fix] Fix mxfp4 triton MoE tp bug (#9473) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
 2025-08-23 01:48:40 -07:00
hlu1andXinyuan Tong dae9a80f43 [fix] Fix mxfp4 weight loading bug with TP sharding in GPT-OSS (#9433) 
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2025-08-21 03:50:51 -07:00