minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
12,537 Commits 2 Branches 0 Tags
1efe9e21649a7784e9c81f4e1fc249dda907e2ac
Commit Graph
8337 Commits
Author SHA1 Message Date
Praneth Paruchuri 1efe9e2164 [Bug Fix] Reject incompatible combination of --disable-cuda-graph-padding and --enable-torch-compile (#23903) 2026-05-12 16:18:36 +08:00
lw9527 8d27ce7371 Optimize uvicorn startup command (#25041) 2026-05-12 00:28:13 -07:00
Yihao Wang b35fd5f104 [fix] skip legacy minicpmv conv template for MiniCPM-V 4.6 (#24998) 2026-05-12 15:27:28 +08:00
Yuwei AnandClaude Opus 4.7 7582237f8e [Tiny Fix] Disable BCG when inner layer_model unresolved (#25021) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-12 14:51:27 +08:00
zhangxiaolei ca3bc05fea Deepseek-v4-Pro share expert tp1 (#24949) 2026-05-11 23:19:35 -07:00
Liangsheng Yin a72d3aef17 [Spec] Multi-layer mamba scatter cleanup; fix positional call bug (#25030) 2026-05-11 22:42:30 -07:00
Liangsheng Yin 1f985c50db [Spec] Rename accepted_indices -> accept_indices; drop _token_id suffix per Rule 5 (#25038) 2026-05-11 22:29:02 -07:00
Ke Bao d7f4761a48 [PD] Refactor hybrid state transfer (#24932) 2026-05-12 13:16:54 +08:00
Zhangheng 91907b7b93 [UnifiedTree]: Fix Unified HiCache tombstone lock release replay (#24972) 2026-05-12 13:16:06 +08:00
Liangsheng Yin 4ad63ad02f [Spec] Rename accepted_drafts -> correct_drafts for unambiguous naming (#24081) 2026-05-11 22:12:40 -07:00
tangcy98andzhangzhang 6bfb365c07 [PD] Rate limit prefill inflight polling warnings (#24967) 
Signed-off-by: zhangzhang <tangchenyu@xiaohongshu.com>
Co-authored-by: zhangzhang <tangchenyu@xiaohongshu.com>
 2026-05-12 12:50:57 +08:00
Ming Yang 6bb79c155b [Linear Attn] Add CUSTOM enum and plugin extensibility for kernel backends (#24937) 2026-05-11 21:46:53 -07:00
Qiaolin Yu cfc41d5b15 Fix kimi k2.5 mla eagle + dp attention (#25033) 2026-05-11 20:58:00 -07:00
Yihao Wang 0f3932c055 [Fix] Qwen3-ASR config: set thinker_config before super().__init__ (#24187) 2026-05-12 11:52:15 +08:00
Liangsheng Yin f526e3fa27 [Spec] Mamba scatter cleanup; fix multi-layer positional bug; dflash naming (#25029) 2026-05-11 20:36:50 -07:00
Jianhong Zhang 10375a1037 [NIXL][XPU] Fix uint64 overflow for mismatched P/D TP sizes (e.g. prefill_tp=1, decode_tp=2) (#24648) 2026-05-12 11:02:24 +08:00
R0CKSTAR 0a37d24e62 [diffusion] hardware: support sage attention backend on MUSA (attn backend, 21/N) (#24752) 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
 2026-05-11 19:50:52 -07:00
shuwenn 5495026a3b [HiCache] feat: default storage prefetch timeout (#23309) 2026-05-11 18:49:35 -07:00
Doğaç Eldenk 186eb42459 Feat: Support SWA (Sliding Window Attention) for EAGLE-3 drafter (#24664) 2026-05-11 18:40:10 -07:00
Doğaç Eldenkandhnyls2002 a75b79e03b Feat: Support newer EAGLE-3 drafters (#24663) 
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
 2026-05-11 18:17:20 -07:00
Liangsheng Yin f3a8189e20 [Spec] Internal rename per N2 v2 naming rule (#25014) 2026-05-11 18:16:26 -07:00
popsiclexu bfc2eda42d [MUSA] Use MUSA-optimized operators in piecewise CUDA graph (#23633) 
Signed-off-by: popsiclexu <zhenxuexu@gmail.com>
 2026-05-11 17:55:27 -07:00
R0CKSTAR 74d70af09a [Apple Silicon] Add Metal kernel support in sgl-kernel (#23449) 
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
 2026-05-11 17:54:27 -07:00
Ethan (Yusheng) SuCursorClaude Opus 4.7
 		e9dea79755 (3/n - prefill optimize)[LoRA][MoE] Optimize virtual experts: remove CPU-GPU sync & multi-block CUDA JIT histogram (#24262) 
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-11 16:36:57 -07:00
Liangsheng Yin 6c3541a914 spec: route idle hidden_size via EagleDraft{,Extend}Input classmethods (#25013) 2026-05-11 15:59:51 -07:00
Liangsheng Yin ce1736fcc6 [Spec] Remove dead kernel params; fix stale comment in trtllm_mla (#25010) 2026-05-11 14:50:46 -07:00
Bruce Changlong Xu d3edfb579b [connector] Add Azure Blob Storage connector (az:// and *.blob.core.windows.net URLs) (#23995) 2026-05-11 14:20:22 -07:00
Jia Guo da0eeb82f2 perf: add --prefill-only-disable-kv-cache to skip KV pool allocation (#23675) 2026-05-11 13:10:24 -07:00
Liangsheng Yin c7e53e68a2 [Spec] Fix ngram metric off-by-1 in num_accepted_drafts_per_req_cpu (#24965) 2026-05-11 12:25:18 -07:00
Yan Ru Pei 4b6f776889 feat(kv-events): publish SWA radix cache events (#24718) 
Signed-off-by: PeaBrane <yanrpei@gmail.com>
 2026-05-11 10:31:45 -07:00
TianheandClaude Sonnet 4.6 95985f983d feat(trace): support SGLANG_TRACE_LEVEL env var for startup trace level (#24716) 
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-11 10:31:03 -07:00
Bingxu ChenandCursor Agent aeb8fefc25 [AMD] Pin cache-dit==1.3.0 in rocm.Dockerfile + AMD CI install script (#24924) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2026-05-11 22:32:13 +08:00
Mick 6d30b571b2 [diffusion] fix: fix single-step flow-match timesteps (#24708) 2026-05-11 18:09:24 +08:00
iridiumineandiridiumine df441b8fea [NPU] Support shared expert dual stream optimization (#23827) 
Co-authored-by: iridiumine <iridiumine@users.noreply.github.com>
 2026-05-11 15:50:15 +08:00
Brayden Zhongandb8zhong 1df9edcd01 Use Torch torch.mm for Deepseek V3.2 Indexer GEMM (#23856) 
Co-authored-by: b8zhong <b8zhong@users.noreply.github.com>
 2026-05-11 00:41:05 -07:00
Brayden Zhongandb8zhong 1d80a1a9fe Use Cute-DSL NVFP4 quantization kernels (#23745) 
Co-authored-by: b8zhong <b8zhong@users.noreply.github.com>
 2026-05-11 00:40:02 -07:00
Cheng WanandClaude Opus 4.7 044bb88a97 fix: SGLANG_RADIX_FORCE_MISS chunk-cache passthrough (#24950) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-11 00:07:46 -07:00
Bingxu Chenandbingxche 3ffb37789a [AMD] Fix DeepSeek import cascade by supporting both pre- and post-#2958 aiter fused_qk_rmsnorm APIs (#24799) 
Co-authored-by: bingxche <cursoragent@cursor.com>
 2026-05-10 23:41:57 -07:00
Liangsheng Yin faad02b3dd spec: centralize EagleDraft{,Extend}Input.hidden_states shape (#24926) 2026-05-10 22:49:20 -07:00
Mick 6e5b4de01a [diffusion] fix: further align ltx2.3 accuracy with tp (#24660) 2026-05-11 13:42:08 +08:00
Thomas ed70226ec1 [Diffusion][NPU][GPU] Fix SANA model execution error (#24798) 2026-05-11 08:41:36 +03:00
Артем Савкинandronnie_zheng 9ec2880eca [NPU] [Bugfix] Wan quantization fix (#24540) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
 2026-05-11 08:32:57 +03:00
Yuwei AnandClaude Opus 4.7 5207f074a4 Breakable Cuda Graph Support for bs > 1 (#24662) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-11 13:28:49 +08:00
Ming Yang 8e2142c15a [MoE] Fix NaN in flashinfer TRT-LLM A2A dispatch by sanitizing padding slots (#24850) 2026-05-10 21:57:43 -07:00
Tejas Dharamsi a6f359d103 [Rerank] Use heapq.nlargest for top_n to avoid full sort (#24871) 2026-05-10 21:48:37 -07:00
gjsheugengjinsongsglang-npu-botgemini-code-assist[bot]gengjinsongronnie_zheng
 		36c93fc6fb [NPU] [Diffusion] Use fused operator to improve Wan model E2E performance. (#24028) 
Co-authored-by: gengjinsong <gengjinsong@huawei.com>
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: gengjinsong <904939979@qq.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
 2026-05-11 07:17:31 +03:00
iridiumineandiridiumine 09a4828db9 [NPU] Fix warmup error with --disable-cuda-graph and mtp (#23819) 
Co-authored-by: iridiumine <iridiumine@users.noreply.github.com>
 2026-05-11 09:53:34 +08:00
McZyWu 4435a23a51 [NPU]adapt multibatch fia ops (#20177) 2026-05-11 09:44:14 +08:00
silencejade 407665a7d4 [NPU] Fix mrope_position computation in Eagle Worker v2 with PlanStream (#23423) 2026-05-11 09:43:37 +08:00
silencejade 0fc9598b3e [NPU] Support radix-cache with mamba-extra-buffer for Qwen3.5 (#23891) 2026-05-11 09:40:44 +08:00