kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-15 11:53:52 +00:00
Code Issues Packages Projects Releases Wiki Activity
11,557 Commits 157 Branches 0 Tags
495ef8ec64b6b937e59cd530ad3150172061a008
Commit Graph

7677 Commits

Author SHA1 Message Date
Mick
495ef8ec64 [diffusion] model: support LTX2.3 two stage (#22182) 2026-04-12 22:15:57 +08:00
Ziang Li
31453bb76a [RL] Fix weight update for mxfp8 flashinfer_cutlass gemm backend (#22484) 2026-04-12 13:02:17 +00:00
Mohammad Miadh Angkad
bcc0c65aa8 [DSA] Hopper FP8 FlashMLA KV padding (#22372) 2026-04-12 02:19:17 -07:00
Kurt Shuster
0e0091c6c8 [server] Add --quantization unquant to explicitly opt out of quantization (#21863) 2026-04-12 02:17:22 -07:00
Wenyao Gao
4dfc8e1c3f VLM: support passing --mm-process-config for all models (#18467) 2026-04-12 17:08:05 +08:00
Liangsheng Yin
f1eb4ca90c Fix streaming session busy check double-counting; add compat CI tests (#22213) 2026-04-12 01:48:16 -07:00
Ke Bao
bc1bfbf607 Fix swa input length limitation (#22597) 2026-04-12 16:03:35 +08:00
Liangsheng Yin
f2377a00cb Add SWA support for runtime busy memory check (#21499) 2026-04-12 00:39:51 -07:00
wufann
19cb918653 [Not-Merge][AMD] GLM-5 performance optimization (#21166) 2026-04-11 23:58:11 -07:00
Hubert Lu
edaa5973d4 [AMD][No-Merge] Simplify fused allreduce + RMSNorm and remove hidden_dim allowlist (#21986) 
Co-authored-by: HAI <hixiao@gmail.com>
 2026-04-11 23:47:08 -07:00
Xinyuan Tong
9a4e8089ff [Whisper] Batch encoder forward for concurrent prefill requests (#22361) 2026-04-12 14:15:14 +08:00
Zhai Feiyue
52750129ef fix prefill tps log accuracy (#22497) 2026-04-11 23:07:30 -07:00
Alex Nails
c6fd9a00c7 [tokenizer] eliminate O(n²) copy in non-incremental streaming (#22567) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-11 23:05:36 -07:00
Prozac614
45472d70cc [diffusion] CI: dynamic load-balanced partitioning for diffusion CI (#15528) 
Co-authored-by: daiweitao <dwti614707404@163.com>
Co-authored-by: SGLang CI <ci@sglang.ai>
 2026-04-12 13:02:43 +08:00
Aurick Qiao
cd2b2364ff [Bugfix] fix model_config deletion (#22281) 2026-04-12 11:24:26 +08:00
Kurt Shuster
8da1cfb30d [lora][moe] Decoupled LoRA MoE backend with Marlin support (#21858) 2026-04-11 14:59:27 -07:00
Ziang Li
78043d4448 [Misc] [MXFP8] Drop sm100 mxfp8 warning (#21881) 2026-04-11 11:11:28 +00:00
Liangsheng Yin
61a62c6503 [mem] Flatten memory checkers into composable per-pool invariant checks (#22562) 2026-04-11 02:56:22 -07:00
dyhsup
8cca9747f5 [diffusion] model: support ERNIE-Image (#22439) 2026-04-11 17:18:11 +08:00
Baizhou Zhang
d14d368191 [Kernel] Set sgl_per_token_group_quant_8bit_v2 as default choice (#22467) 2026-04-11 01:59:57 -07:00
cctry
f855a0bde6 Introduce CUDA graph debug mode with breakable CUDA graph (#19102) 
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Cheng Wan <chwan@rice.edu>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-11 00:36:56 -07:00
Liangsheng Yin
d11da2403c Add hisparse staging + decode offload guards to is_fully_idle() (#22577) 2026-04-11 00:12:10 -07:00
sushil Dubey
e26c73c4e9 [diffusion] platform: support Intel XPU (#17920) 
Signed-off-by: sushil.dubey <sushil.dubey@intel.com>
Signed-off-by: Sushil Dubey <sushil.dubey@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-04-11 15:09:02 +08:00
YC Yen-Ching Tseng
cf1436d6ae [AMD] Diffusion - Enabel rocm miopen tuning on vae (#22428) 2026-04-10 22:47:25 -07:00
Jacob0226
7e4e1dcd7a [AMD] Fuse RMSNorm + FP8 per-token quant for GLM-4.7-FP8 (#21403) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-10 22:45:31 -07:00
Khoa Pham
aeeff58cd4 [Spec][Ngram] Clean up unused stateless batchMatch (#22487) 2026-04-10 21:52:56 -07:00
Khoa Pham
04bd8e1218 [Spec][Ngram] Return token counts in list_external_corpora API (#22471) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-10 21:50:02 -07:00
Zhangheng
f2af00d05a [HiSparse-pd] Add device-buffer budget and fix logical pool admission in decode side (#22453) 2026-04-11 12:30:38 +08:00
Alex Nails
8eac618a8d [tokenizer] lazy text accumulation + use deltas directly for streaming (#22548) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-10 21:26:04 -07:00
Liangsheng Yin
c7f93a2ce7 [metrics] Add PoolStats.update_scheduler_stats to deduplicate metrics assignment (#22559) 2026-04-10 21:04:18 -07:00
Bi Xue
d30b3efa84 [sgl] _ATTN_TP and _ATTN_CP use message queue for broadcast on CPU (#22205) 2026-04-10 20:52:49 -07:00
Xinyuan Tong
7c6db40540 Fix tool call constrained decoding and parsing for models with native formats (#21593) 2026-04-10 20:37:23 -07:00
Liangsheng Yin
c2821dfbe9 [mem] Introduce PoolStats dataclass; unify pool metrics and token_usage (#22554) 2026-04-10 20:35:50 -07:00
Yuhao Yang
16f306fd85 [VLM] GPU Image Preprocessing for Kimi-K2.5 (#22368) 2026-04-11 11:13:30 +08:00
Yilong Zhao
58f863956c cuda graph: adjust capture time num-non-padded-tokens to align capture with replay (#22404) 2026-04-11 10:27:50 +08:00
Mick
0b4f5c9fcb [diffusion] CI: improve readability and fix bug of early-return (#22507) 2026-04-11 10:08:44 +08:00
Alison Shao
75223c5404 [Diffusion][CI] Fix nunchaku unit test broken by #22365 (#22560) 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
 2026-04-10 17:49:56 -07:00
Liangsheng Yin
b4a1d8fd71 [mem] Fix idle token_usage missing mamba_usage; add FIXME for naming (#22555) 2026-04-10 16:20:33 -07:00
Alex Nails
0af9166474 [tokenizer] improve non streaming request processing + some small fixes. (#20310) 2026-04-10 15:46:12 -07:00
ori
f7a1740101 [MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine) (#22051) 
Co-authored-by: zhiguo.qin <zhiguo.qin@mthreads.com>
 2026-04-10 14:18:39 -07:00
Minglei Zhu
6af34b95b6 perf: precompute FA3 scheduler_metadata to eliminate per-layer prepare_varlen_num_blocks (#21104) 
Co-authored-by: zminglei <zminglei@linkedin.com>
 2026-04-10 13:57:54 -07:00
Zhongdongming Dai
4ace144fae feat: update ModelExpress metadata API to SourceIdentity-based schema (#21222) 2026-04-10 13:45:05 -07:00
Cheng Wan
6d95602ea3 Reduce GPU memory for MoE parallel groups (#22515) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-10 13:23:23 -07:00
satyamk7054
059b287e25 Add offline auto-tuning for LoRA CSGMV kernel (#20391) 
Co-authored-by: Satyam Kumar <satyamk@linkedin.com>
 2026-04-10 13:10:43 -07:00
Qiaolin Yu
d8831355a3 Fix multi_layer_eagle_worker_v2 draft extend selection, add chain style multi layer mtp test (#22340) 
Co-authored-by: 0xNullPath <luyan@nvidia.com>
 2026-04-10 12:44:52 -07:00
Trevor Morris
7dbd0dd9f0 MiniMax-M2.5 - Support dp attention, dp reduce scatter, FP4 all gather, AR fusion in prepare_attn (#20067) 2026-04-10 12:41:27 -07:00
KrishnanPrash
a937ec31be fix: server crash when stop_token_ids contains null (#22175) 
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
 2026-04-10 11:42:23 -07:00
Jia Guo
5cb4ea1d4d perf: enable inductor combo_kernels for horizontal fusion (#21977) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-11 01:01:14 +08:00
Tarushii Goel
2ba94136ce [sgl] improve mamba_track_indices perf in specdec (#22380) 2026-04-11 00:39:53 +08:00
Bi Xue
f652135d52 [sgl] fix using symmetric memory issues for attention_tp (#22286) 2026-04-11 00:26:18 +08:00