minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
11,198 Commits 3 Branches 0 Tags
f25bf86065b65aeb213c6dc1f0565b32922d14af
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Xiaoyu Zhang cdd7d6a227 Remove obsolete sgl-kernel legacy paths (#21528) 2026-04-01 09:00:20 +08:00
Xiaoyu Zhang 505eb312ec Revert "DeepSeek-R1-0528-w4a8: DeepEP Low Latency Dispatch Adopts FP8 Communication" (#21719) 2026-03-31 10:22:01 +08:00
Xiaoyu Zhangandgemini-code-assist[bot] 516cff97a3 [Diffusion] Align diffusion benchmark skill presets with nightly comparison cases (#21616) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-03-29 12:12:17 +08:00
Xiaoyu Zhang 9238bd08a2 [CI] Register missing jit_kernel test files (#21547) 2026-03-27 19:39:08 +08:00
Xiaoyu Zhang d633ab7349 [Diffusion] Add qknorm rope fuse kernel (#21440) 2026-03-27 14:27:08 +08:00
Xiaoyu Zhang e8d46f145c Opt jit qknorm_across_heads cuda kernel (#21503) 2026-03-27 13:30:46 +08:00
Xiaoyu Zhang 7ca015fe65 [Diffusion] Refactor diffusion JIT kernel test layout and narrow CI triggers (#21385) 2026-03-26 15:02:02 +08:00
Xiaoyu Zhang 6f2b51ade1 [Diffusion] Optimize diffusion Triton rotary embedding by processing multiple heads per token (#21387) 2026-03-26 08:59:25 +08:00
Xiaoyu Zhang 68f7f00174 [Diffusion] Speed up Qwen select01 Triton modulation kernels (#21318) 2026-03-25 20:48:39 +08:00
Xiaoyu Zhang 689e9ef05c [Diffusion] Add AKO4ALL kernel optimization skill (#21323) 2026-03-25 18:46:21 +08:00
Xiaoyu Zhang e4ad10520b [diffusion] Skip automatic Wan/MOVA DiT layerwise offload on high-end GPUs (#21248) 2026-03-25 18:45:30 +08:00
Xiaoyu Zhang 69f02e36e8 [diffusion] Fix torch.zeros typo in causal wan (#21250) 2026-03-24 14:39:16 +08:00
Xiaoyu Zhang d9f97b2115 Refine diffusion skills and align JIT kernel docs with the new CI flow (#21283) 2026-03-24 14:38:36 +08:00
Xiaoyu Zhang a94d67d44b [SKILL] fix(bench): Support model-specific DenoisingStage variants in… (#21137) 2026-03-23 12:08:00 +08:00
Xiaoyu Zhangandgemini-code-assist[bot] c1fe5de69c [Diffusion] Clean up diffusion Triton kernels and modernize custom op registration (#21122) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-03-22 22:38:57 +08:00
Xiaoyu Zhang 766d225fcc Add SGLang CUDA crash API logging inspired by FlashInfer (#20910) 2026-03-22 16:39:40 +08:00
Xiaoyu ZhangandMick 1b65c0d259 [Diffusion] Fix torch.compile RMSNorm fallback for Z-Image (#20962) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-03-22 15:38:22 +08:00
Xiaoyu Zhang c076968c52 [CI] Remove obsolete AOT-only jit-kernel benchmarks after sgl-kernel 4.0 (#21075) 2026-03-21 13:40:42 +08:00
Xiaoyu Zhang cf60c5bd15 [CI] Fix jit_kernel benchmark ci (#20990) 2026-03-20 16:40:20 +08:00
Xiaoyu Zhang 20a23e3173 [SKILL] Refine kernel authoring docs and validate add-jit-kernel / add-sgl-kernel end to end with Codex (#20867) 2026-03-18 23:00:33 +08:00
Xiaoyu Zhang 6489f77733 [Diffusion] Fix compile graph broken by flashinfer rope (#20699) 2026-03-16 23:14:27 +08:00
Xiaoyu ZhangandBaizhou Zhang 15097c5c3b Release sglang kernel 0.4.0 (#20440) 
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
 2026-03-16 20:34:58 +08:00
Xiaoyu Zhang 3055b6906d [Diffusion] Document torch.compile graph-break checks in diffusion benchmark skills (#20681) 2026-03-16 17:41:40 +08:00
Xiaoyu Zhang e1eb25880f [Diffusion] Add a benchmark for rmsnorm/fuse_add_rmsnorm (#20632) 2026-03-16 09:50:33 +08:00
Xiaoyu Zhang 45dd06f4e0 Remove insecure auto-format label workflow (#20629) 2026-03-15 21:04:29 +08:00
Xiaoyu Zhang 5ab2cfe9a8 [Diffusion] Clean upstream fa3 in hopper (#20576) 2026-03-14 23:41:23 +08:00
Xiaoyu Zhang 25e38216b6 [kernel slimming] Clean many useless sgl-kernel deprecated kernels (#20277) 2026-03-14 16:45:54 +08:00
Xiaoyu Zhang f9e4221b71 [Diffusion] add mova and hunyuanvideo to perf skills (#20563) 2026-03-14 13:49:50 +08:00
Xiaoyu Zhang be7a0311a0 [Diffusion] Fix and validate diffusion skills benchmarking/profiling workflow (#20528) 2026-03-13 21:11:37 +08:00
Xiaoyu ZhangandYihan Chen e00328d1e5 [Diffusion] Opt qwen-image-edit with fuse_residual_layernorm_scale_shift_gate_select01_kernel (#20395) 
Co-authored-by: Yihan Chen <yingluosanqian@gmail.com>
 2026-03-13 13:15:22 +08:00
Xiaoyu Zhang 7ecf07b8f4 [jit_kernel] Temporarily Skip Flaky JIT Kernel GDN Test and Add PR Label (#20436) 2026-03-13 09:34:22 +08:00
Xiaoyu ZhangandBaizhou Zhang 680d9d98e4 Fix cutedsl ci error (#20309) 
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
 2026-03-11 16:17:35 +08:00
Xiaoyu Zhang 60cc06297e [4/n jit_kernel restruct] speed up CI tests and add benchmark workflow (#20268) 2026-03-10 21:37:41 +08:00
Xiaoyu Zhang 51d9d34977 [2/n jit_kernel restruct] unify rotary embedding entrypoints under rope.py (#20247) 2026-03-10 17:49:57 +08:00
Xiaoyu Zhang 8517da5d08 [3/n jit_kernel restruct] Clean up benchmark naming and benchmarking helpers (#20250) 2026-03-10 16:39:03 +08:00
Xiaoyu Zhang c812504b92 [1/n jit_kernel restruct] unify cache usage and clean up naming in ngram_embedding (#20244) 2026-03-10 15:53:43 +08:00
Xiaoyu Zhang fd79cd8d9c [Skills] Refine jit_kernel and sgl-kernel skills (#20095) 2026-03-07 22:54:01 +08:00
Xiaoyu ZhangandMick 6d22c9f369 [Diffusion] Move hf kernels diffusion cuda kernels skills to SGLD (#20001) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-03-06 22:16:06 +08:00
Xiaoyu ZhangandMick 9795b4cd5b [Diffusion] Open t5 encoder parallel folding for wan2.2 and mova video (#18493) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-03-05 10:18:00 +08:00
Xiaoyu Zhang 4348976f80 [Diffusion] Refactor diffusion benchmark/profile skill to reuse diffusion-perf skill and clarify profiling trigger (#19783) 2026-03-04 10:54:42 +08:00
Xiaoyu Zhang 115e9a1acd [Diffusion] Delete useless _ulysses_input_split func (#19786) 2026-03-04 10:45:11 +08:00
Xiaoyu Zhang 145ae518ac [Diffusion] Revert 18619 (#19510) 2026-03-03 08:15:15 +08:00
Xiaoyu Zhang 51ee17ce44 [diffusion] move skills dir (#19697) 2026-03-03 02:51:29 +08:00
Xiaoyu Zhang 53de53fb53 [jit_kernel] Tiny unify jit_kernel tests style (#19694) 2026-03-02 21:33:59 +08:00
Xiaoyu Zhang e42fa009d4 [Diffusion] diffusion profile and opt skills (#19540) 2026-03-02 15:06:29 +08:00
Xiaoyu Zhang fe971b620a [Diffusion] Add SGL-D diffusion efficient kernel skills (#19473) 2026-02-27 11:42:13 +08:00
Xiaoyu Zhang 054bd71086 [sgl-kernel slimming] remove sgl-kernel moe-wna16-marlin (#19379) 2026-02-27 09:17:46 +08:00
Xiaoyu Zhang 74c8e7b215 refactor(jit_kernel): reduce duplication and separate test code (#19323) 2026-02-26 18:30:49 +08:00
Xiaoyu Zhang 914ed34757 update jit_kernel codeowners (#19385) 2026-02-26 10:36:34 +08:00
Xiaoyu Zhang ab7071b545 [SKILL] Better claude skills for sgl-kernel and jit-kernel (#19302) 2026-02-25 15:26:55 +08:00
Xiaoyu Zhang 694924b878 Update .gitignore to remove '.claude/' (#19296) 2026-02-25 11:51:50 +08:00
Xiaoyu Zhang 9dff933164 [Kernel Slimming] Remove sgl-kernel AOT marlin kernels (#19241) 2026-02-25 10:08:22 +08:00
Xiaoyu Zhang e0e0cad6bc [Diffusion] Match rotary_embedding module name style (#19179) 2026-02-23 21:02:34 +08:00
Xiaoyu Zhang 2717393681 [Refactor] Split rotary_embedding.py into a modular package (#19144) 2026-02-23 20:05:29 +08:00
Xiaoyu Zhang 66497ab0aa [Diffusion] Restruct and clean Diffusion rotary embedding (#19064) 2026-02-21 21:41:47 +08:00
Xiaoyu Zhang 19aa19b111 [diffusion] refactor: refactor diffusion triton kernels (#18966) 2026-02-19 17:03:44 +08:00
Xiaoyu Zhang 390c154306 [Tiny fix] Super tiny fix mul_add naive forward bug (#18964) 2026-02-18 16:18:43 +08:00
Xiaoyu Zhang 513c12d23f Remove unused fast-hadamard-transform PyTorch extension sources (#18927) 2026-02-18 15:51:07 +08:00
Xiaoyu Zhang d3bae71e3f Add claude skills for sgl-kernel and jit-kernel (#18855) 2026-02-15 15:14:03 -08:00
Xiaoyu Zhang 4067d9487d [diffusion] feat: opt vae decode with channels_last_3d (#18540) 2026-02-14 23:19:45 +08:00
Xiaoyu Zhang c29394e3c8 [kernel slimming] Move fast_hadamard_transform to jit_kernel (#18475) 2026-02-14 23:06:21 +08:00
Xiaoyu Zhang 013a199bc6 [CI] Skip cutedsl gdn performance test in jit_kernel ci (#18783) 2026-02-13 15:49:30 +08:00
Xiaoyu Zhang 9e9e949261 speed up sgl-kernel build (#18586) 2026-02-12 23:43:22 +08:00
Xiaoyu Zhang bec7fe9e65 [sgl-kernel] upgrade deepgemm (#18362) 2026-02-10 21:31:30 +08:00
Xiaoyu Zhangandyihanc baec650462 [Diffusion] Apply fused_norm_scale_shift to LTX2/MOVA (#18257) 
Co-authored-by: yihanc <yingluosanqian@gmail.com>
 2026-02-07 17:28:42 +08:00
Xiaoyu Zhang dff3ba202a [Diffusion] Support layerwise offload for mova (#18272) 2026-02-05 13:16:07 +08:00
Xiaoyu Zhang 2e9d0442e2 [diffusion] update code owner (#18247) 2026-02-04 19:12:32 +08:00
Xiaoyu Zhang eedd472025 [Diffusion] fix serving image_edit get input image bug (#18109) 2026-02-03 12:17:16 +08:00
Xiaoyu Zhang a1bbc892af [Diffsuion & JIT_kernel] QKNorm cross heads kernel (#18073) 2026-02-03 10:03:17 +08:00
Xiaoyu Zhang a0757c9624 [Diffusion] Fix Ring Parallel bug with FA4 (#18062) 2026-02-02 17:06:51 +08:00
Xiaoyu Zhang 22aad4e2c4 [Diffusion] Fix FLUX.1-schnell time embedding argument mismatch (#17988) 2026-01-31 11:47:27 +08:00
Xiaoyu Zhang abf13ccc11 [Diffusion] Fix lora default lora_scale bug (#17982) 2026-01-30 22:04:54 +08:00
Xiaoyu Zhang c08b54a575 [JIT kernel] Update jit_kernel cache and develop doc (#17842) 2026-01-28 15:09:47 +08:00
Xiaoyu Zhang fb74e43707 [Diffusion] Delete sgl-kernel outdated time_embedding kernel (#17278) 2026-01-28 14:18:53 +08:00
Xiaoyu Zhang 67fb492c9a [CI] Fix test_moe_fused_gate error (#17844) 2026-01-28 12:03:17 +08:00
Xiaoyu Zhang 331a22427c [Diffusion] glm-image apply flashinfer rope (#17689) 2026-01-28 08:51:37 +08:00
Xiaoyu Zhang 3992a023e6 Move fa4 from sgl-kernel to jit kernel (#17353) 2026-01-24 15:25:03 +08:00
Xiaoyu Zhang 7a4bb0d516 [Diffusion] Add diffusion time embedding to jit kernel (#17658) 2026-01-24 14:27:08 +08:00
Xiaoyu Zhang 5324027007 [Diffusion] Make the apply_qknorm function easier to use (#17537) 2026-01-22 22:32:15 +08:00
Xiaoyu Zhang 590969ee9c [Diffusion] Support select fa2 backend in hopper (#17514) 2026-01-22 08:23:53 +08:00
Xiaoyu Zhang 19089aa431 [Diffusion] Refactor diffusion is_cuda check (#17498) 2026-01-21 23:02:24 +08:00
Xiaoyu Zhangandgemini-code-assist[bot] cc410a1088 [Diffusion] Apply qknorm to flux2 and apply lightx2v rms_norm_one_pass kernel(without residual) (#17305) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-19 21:25:33 +08:00
Xiaoyu Zhang a3d9a21882 Revert "[Perf] fuse q, k norm for Flux2Attention (#17241)" (#17332) 2026-01-19 15:24:11 +08:00
Xiaoyu Zhang 330605cc88 [Diffusion] Apply jit qk_norm to flux1 (#17296) 2026-01-19 00:28:36 +08:00
Xiaoyu Zhang 2cdd4370bc [Diffusion] Move diffusion time embedding to jit kernel (#16879) 2026-01-17 12:21:22 +08:00
Xiaoyu Zhang 6ee970a365 [Diffusion] Hot fix broken output_path default value (#17180) 2026-01-16 12:14:09 +08:00
Xiaoyu Zhang 0d904ef44c [diffusion] fix: fix fsdp tp load make param miss parallel meta data (#17058) 2026-01-15 00:12:33 +08:00
Xiaoyu Zhang 2ab3ed3e9e Fix sgl-kernel per_token_quant fp8 kernel scale shared_memory bug (#16886) 2026-01-13 23:22:05 +08:00
Xiaoyu Zhang 740d3c0b39 [Diffusion] Remove useless dependency in diffusion (#16967) 2026-01-13 17:25:53 +08:00
Xiaoyu Zhangandgemini-code-assist[bot] 9d4d57dbfa [Diffusion] Tiny rename parallel_groups (#16743) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-09 15:08:25 +08:00
Xiaoyu ZhangandMick 294ff71d18 [Diffusion] Avoid cpu2gpu sync in flashinfer rope and apply flashinfer rope to wanvideo (#16668) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-08 22:44:38 +08:00
Xiaoyu Zhang 5a5cece561 [Diffusion] clean useless and buggy set_seq_parallel_pg in yunchang (#16669) 2026-01-08 11:08:34 +08:00
Xiaoyu ZhangandMick 32a6540afc [Diffusion] Fix Ulysses/Ring process group construction under TP to enable correct Wan2.2 tensor parallelism (#16532) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-07 20:52:36 +08:00
Xiaoyu Zhang 62d0280f62 Tiny fix readme (#16654) 2026-01-07 20:41:07 +08:00
Xiaoyu Zhang 5e5b1183ed [Diffusion] Ring Attention support sage backend (#16496) 2026-01-06 14:45:53 +08:00
Xiaoyu Zhang 4ea6a11c83 [CI] Fail wheel build when sgl-kernel artifacts are missing (#16450) 2026-01-04 21:46:40 -08:00
Xiaoyu Zhang 520c048d55 [diffusion] CI: add script for automatically generation ci perf baseline (#16389) 2026-01-05 13:18:35 +08:00
Xiaoyu Zhang 0fee6bc632 [JIT kernel] Apply jit per_tensor_quant_fp8 kernel (#15836) 2026-01-05 10:15:00 +08:00
Xiaoyu ZhangandMick d0fb24ee7b [Diffusion] Flux2 tp support (#16219) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-03 17:02:27 +08:00
Xiaoyu Zhang 1cfd2b2ded [diffusion] chore: remove redundant ulysses nccl warmup (#16301) 2026-01-03 00:19:35 +08:00