minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity
15,195 Commits 3 Branches 0 Tags
0fe2dbd42caeb627bd8aca162dab7763d292fda9
Commit Graph
77 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Xiaoyu ZhangandClaude Fable 5 e9ef06c560 [Kernel] Migrate top-level srt/layers stray kernels to sglang.kernels (RFC #29630, Phase 2.5, 3/7) (#30787) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-14 09:20:59 +08:00
Xiaoyu ZhangandClaude Fable 5 ee464fedc6 [Kernel] Migrate scattered MoE kernels to sglang.kernels (RFC #29630, Phase 2.5, 2/7) (#30786) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-14 09:03:21 +08:00
Xiaoyu ZhangandClaude Opus 4.8 4c997310f5 [Kernel] Hotfix: update sgl-kernel imports of relocated fp8_kernel (RFC #29630 #30784) (#31089) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-14 08:41:23 +08:00
Xiaoyu ZhangandClaude Fable 5 874fc07d9b [Kernel] Migrate scattered quantization kernels to sglang.kernels (RFC #29630, Phase 2.5, 1/7) (#30784) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-13 16:17:01 +08:00
Xiaoyu Zhang 65abb23842 Add diffusion BCG prompt conditioning guard (#30782) 2026-07-11 13:14:31 +08:00
Xiaoyu ZhangandClaude Opus 4.8 6ed9843b57 [Kernel] Introduce sglang.kernels namespace and migrate scattered triton_ops kernels (RFC #29630, Phase 2) (#30044) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-10 21:41:08 +08:00
Xiaoyu Zhang e9493a015c Fix diffusion BCG lifetime and add Z-Image-Turbo CI (#30584) 2026-07-10 21:19:59 +08:00
Xiaoyu Zhang b8ca06fdad Fix zero expert routed ids for MoE backends (#30387) 2026-07-08 21:23:25 +08:00
Xiaoyu ZhangBBufClaude Opus 4.8BBuf
 		33c3dfd7e0 [diffusion] Enable breakable CUDA graph (BCG) for diffusion DiTs (#27436) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: BBuf <bbuf@sglang.local>
 2026-07-08 14:45:48 +08:00
Xiaoyu ZhangandZijie Xia ead1e490b5 [Doc] Add LongCat 2.0 FP8 cookbook (#30320) 
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
 2026-07-07 11:48:13 -07:00
Xiaoyu Zhangsunjiaqi11Ke Bao
 		e339c83f82 [Model] Support LongCat 2.0 FP8 (#30275) 
Co-authored-by: sunjiaqi11 <sunjiaqi11@meituan.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
 2026-07-07 19:51:12 +08:00
Xiaoyu ZhangandClaude Opus 4.8 1da7d3a50b [MoE] Retire the AOT moe_fused_gate / kimi_k2_moe_fused_gate gate kernels (#26771) (#29997) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-07-07 13:53:17 +08:00
Xiaoyu Zhang 931b00f1b0 [diffusion] Clean up duplicate helper definitions (#30159) 2026-07-05 22:05:11 +08:00
Xiaoyu Zhang 6dd0cefb2a [CI] Revert ModelOpt NVFP4 threshold relax (#29844) 2026-07-04 21:17:32 +08:00
Xiaoyu ZhangandClaude Opus 4.8 a2d7eb303e [MoE] Consolidate ungrouped + grouped gate/topk onto one Triton router (#26771) — faster than AOT on B200/H100/H200, at parity with flashinfer (#29771) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-07-03 11:18:59 +08:00
Xiaoyu Zhang b276a9acee chore: cleanup garbage code (#29770) 2026-07-02 16:14:01 +08:00
Xiaoyu ZhangKhoa PhamClaude Opus 4.8Mohammad Miadh Angkad
 		df0dfbaa45 [Kernel] Strengthen kernel shape coverage (#29636) 
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
 2026-07-01 15:44:20 +08:00
Xiaoyu Zhang 8205aa3603 chore: clean diffusion dead code (#29789) 2026-07-01 15:42:16 +08:00
Xiaoyu Zhang 47ae1241d3 [CI] Relax ModelOpt NVFP4 diffusion consistency thresholds (#29767) 2026-07-01 14:45:08 +08:00
Xiaoyu Zhang fcb9f229b3 [KDA-Pilot] Add LTX2 QKNorm split-RoPE CUDA fast path (#29708) 2026-07-01 14:42:07 +08:00
Xiaoyu ZhangandClaude Opus 4.8 3add35e26d [Diffusion] Reuse shared AlignedVector and tidy jit_kernel/diffusion (#29664) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-30 11:38:22 +08:00
Xiaoyu Zhang c36f166364 [skill] Remove outdated llm-serving-auto-benchmark skill (#29487) 2026-06-27 14:19:11 +08:00
Xiaoyu ZhangandClaude Opus 4.8 495f13fa12 [KDA-Pilot] Add diffusion residual-gate CUDA fast path for LTX2 (#29361) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-27 12:59:41 +08:00
Xiaoyu Zhang 8524678889 Fix MiniMax MSA fallback when fmha plan is unavailable (#29250) 2026-06-26 23:14:31 +08:00
Xiaoyu Zhang 18b0e5757e [Diffusion] Fuse LTX2 Ada values (#29390) 2026-06-26 23:13:15 +08:00
Xiaoyu ZhangandClaude Opus 4.8 5996b54bd3 [KDA-Pilot] Add diffusion causal Conv3D cat-pad CUDA fast path for Cosmos3 (#29281) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-26 15:06:49 +08:00
Xiaoyu Zhang 4d06d4c97f Sync Gemma4 hardware table with Blackwell recipes (#29266) 2026-06-25 22:57:33 +08:00
Xiaoyu Zhangjingyu-mlClaude Opus 4.8
 		52c32035eb [diffusion] Add Qwen-Image ModelOpt NVFP4 support (#28928) 
Co-authored-by: jingyu-ml <jingyux@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-25 22:56:09 +08:00
Xiaoyu Zhang ddda4f9028 [Bugfix] Fix Ministral3 init argument forwarding (#29111) 2026-06-25 18:26:45 +08:00
Xiaoyu Zhang 7c9804ef21 Add MiMo V2.5 Blackwell vision FA4 recipe (#29253) 2026-06-25 13:47:32 +08:00
Xiaoyu Zhang efbe67d237 Tune Gemma4 26B-A4B B200 memory recipe (#29252) 2026-06-25 11:31:25 +08:00
Xiaoyu Zhang 26e1d4d847 [KDA-Pilot] Add B200 diffusion norm-scale-shift CUDA fast path for Qwen-Image (#27392) 2026-06-24 14:38:36 +08:00
Xiaoyu Zhang 534ac98eb2 [codex] Optimize DMD Wan auto residency on high-memory GPUs (#28780) 2026-06-24 14:03:23 +08:00
Xiaoyu Zhang 31d71c47af [Diffusion] Fix SANA VAE dtype and TurboWan backend selection (#28769) 2026-06-23 22:57:08 +08:00
Xiaoyu Zhang 6b2c730bf7 [codex] Fix DSA indexer in prefill piecewise CUDA graph (#28644) 2026-06-22 22:39:21 +08:00
Xiaoyu Zhang b43bd6824f [B300] Enable FlashInfer allreduce for Qwen3-VL MoE (#28786) 2026-06-22 22:38:45 +08:00
Xiaoyu Zhang 0c9e775f2c [Diffusion] Fix FastWan2.1 default 480p resolution (#28733) 2026-06-22 18:43:24 +08:00
Xiaoyu Zhang c1416bb3ee [Diffusion] Keep FastHunyuan VAE resident on high-memory GPUs (#28773) 2026-06-20 15:54:06 +08:00
Xiaoyu Zhang 31c0a98066 [codex] Update diffusion skills for latest main (#28711) 2026-06-19 16:37:59 +08:00
Xiaoyu Zhang b6be5dd20f [codex] Remove outdated SGLang SOTA skill (#28719) 2026-06-19 16:26:44 +08:00
Xiaoyu Zhang 3b417d3999 Revert "[Diffusion] FLUX: fuse FeedForward GELU into up-proj GEMM (cublasLt epilogue)" (#28708) 2026-06-19 13:44:57 +08:00
Xiaoyu ZhangandClaude Opus 4.8 7da92e1112 [diffusion] Sana: pack self-attn q/k/v and cross-attn k/v into single GEMMs (#28393) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-19 13:25:52 +08:00
Xiaoyu Zhang 7e20e25848 [docs] Add B300 cookbook deployment options (#28697) 2026-06-18 21:52:45 -07:00
Xiaoyu Zhang b7d7dfb4ed [Bugfix] Fix Intern-S1 FP8 expert count lookup (#28629) 2026-06-18 17:49:59 +08:00
Xiaoyu Zhang c5b9106c1a [perf] Use default torch compile mode for Wan2.2 T2V A14B (#28304) 2026-06-16 15:45:00 +08:00
Xiaoyu ZhangBBufClaude Opus 4.8
 		07b9108348 [Diffusion] FLUX: fuse FeedForward GELU into up-proj GEMM (cublasLt epilogue) (#28166) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-15 13:00:26 +08:00
Xiaoyu ZhangandBBuf 06e0df5899 Optimize Qwen3 Next FP8 MoE on H200 (#26204) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-06-11 22:18:43 +08:00
Xiaoyu ZhangandBBuf 1a6b5561db Fix MLA scaling when YARN scaling is disabled (#26203) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-06-11 22:17:55 +08:00
Xiaoyu Zhang d571e076fa [codex] Centralize more inline Triton kernels (#27429) 2026-06-11 22:17:26 +08:00
Xiaoyu ZhangandClaude Opus 4.8 aa18a68ac5 [diffusion] Run LTX-2 VAE decode in channels_last_3d (faster decode, lower peak memory) (#27431) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-09 23:26:40 +08:00
Xiaoyu Zhangandxiaoyu.zhang 6c2770149b [diffusion] Fix native text-encoder loading for T5/UMT5 encoder-decoder models (#27432) 
Co-authored-by: xiaoyu.zhang <xiaoyu.zhang@radixark.net>
 2026-06-08 12:23:16 +08:00
Xiaoyu Zhang 5bf7dd8e4a Update SGLang diffusion skills (#27496) 2026-06-08 12:22:45 +08:00
Xiaoyu Zhang ff8b97406d [diffusion] optimize: precompute ideogram4 denoising metadata (#27443) 2026-06-07 14:27:41 +08:00
Xiaoyu Zhang 2c3e84affe [Diffusion] Enable Cosmos3 denoising profiling (#27439) 2026-06-07 10:32:28 +08:00
Xiaoyu ZhangBBufClaude Opus 4.8
 		bd7fea0740 [diffusion] Fix LingBot-World crash on camera control with ulysses>1 (#27437) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-06 22:02:29 +08:00
Xiaoyu Zhang 7c6f9542c7 [Diffusion] Avoid GPU syncs in UniPC scheduler (#27440) 2026-06-06 22:01:41 +08:00
Xiaoyu ZhangandBBuf f57f8a8afd Optimize Gemma4 H200 MoE and extend attention (#26588) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-06-06 14:14:25 +08:00
Xiaoyu ZhangCodexBBuf
 		e513c13e2e Optimize ngram decode token table update (#24756) 
Co-authored-by: Codex <codex@example.com>
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-06-06 14:13:45 +08:00
Xiaoyu ZhangCodexBBuf
 		84e1108312 Optimize ngram decode id computation (#24757) 
Co-authored-by: Codex <codex@example.com>
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-06-02 17:37:34 +08:00
Xiaoyu ZhangandBBuf 3ea1ba5b15 [GDN] Optimize prefill QKV split dispatch (#26206) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-06-02 16:48:31 +08:00
Xiaoyu ZhangandBBuf 559581b383 [codex] Centralize Triton utility kernels (#26000) 
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-06-02 16:47:45 +08:00
Xiaoyu ZhangCodexBBuf
 		e279b0bf72 Optimize large add_constant tensors (#24755) 
Co-authored-by: Codex <codex@example.com>
Co-authored-by: BBuf <xiaoyu.zhang@radixark.net>
 2026-05-30 22:25:19 +08:00
Xiaoyu Zhang e60f799b40 Enable Kimi-K2.5 piecewise CUDA graph (#26382) 2026-05-27 22:51:33 -07:00
Xiaoyu ZhangandBBuf 121cc09405 [diffusion] Add CFG gating for denoising (#25848) 
Co-authored-by: BBuf <bbuf@example.com>
 2026-05-25 22:57:09 +08:00
Xiaoyu ZhangandBBuf 85f9522e36 [diffusion] Cache fp32 layernorm params (#25847) 
Co-authored-by: BBuf <bbuf@example.com>
 2026-05-25 22:56:39 +08:00
Xiaoyu Zhang 533ef41112 [Diffusion] Default NVFP4 backend to FlashInfer TRTLLM (#25523) 2026-05-25 18:14:06 +08:00
Xiaoyu Zhang 0b65588c18 [diffusion] Clean up VSA attention hot path (#25514) 2026-05-24 16:46:03 +08:00
Xiaoyu Zhang 75427c9ca4 Route concat MLA to JIT and remove unused downcast (#25843) 2026-05-23 14:30:43 +08:00
Xiaoyu Zhang ccbbae00ea [codex] Reland Wan2.2 ModelOpt CI checkpoints (#25857) 2026-05-20 22:15:25 +08:00
Xiaoyu Zhang af22390af7 [codex] Align diffusion skills with nightly Nvidia benchmarks (#25842) 2026-05-20 12:18:05 +08:00
Xiaoyu Zhang 80fc524809 [diffusion] quant: update Wan2.2 modelOpt CI checkpoints (#25483) 2026-05-20 09:05:39 +08:00
Xiaoyu Zhang 0e4d1b49d3 [Codex] Remove stale DeepSeek V4 JIT kernels (#25764) 2026-05-19 20:04:32 +08:00
Xiaoyu Zhang 31e324391b [Codex] Opt Mistral Large performace (#24611) 2026-05-19 10:59:51 +08:00
Xiaoyu ZhangandCodex 2424303dfb [codex] Optimize hidden-size 512 RMSNorm dispatch (#24710) 
Co-authored-by: Codex <codex@example.com>
 2026-05-19 09:26:10 +08:00
Xiaoyu ZhangandCodex 2fc217df4d [codex] Split diffusion quant CI coverage (#24599) 
Co-authored-by: Codex <codex@example.com>
 2026-05-16 22:05:02 +08:00
Xiaoyu Zhang 93bacc25ed [codex] Optimize LTX2 split rotary kernel (#24732) 2026-05-16 20:58:38 +08:00
Xiaoyu ZhangandBBuf Codex aaaad9e7c2 [Codex] Diffusion tune Hunyuan3D shape export chunks (#24358) 
Co-authored-by: BBuf Codex <bbuf-codex@users.noreply.github.com>
 2026-05-15 15:31:01 +08:00