kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-01 04:08:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
11,612 Commits 157 Branches 0 Tags
a9a2ae4a685bcba70b9329f9335561ba2e3f9413
Commit Graph

7716 Commits

Author SHA1 Message Date
Xuwei
a9a2ae4a68 [Anthropic] Fix clock mismatch in received_time causing negative Prometheus metrics (#22247) 
Signed-off-by: Xuwei Li <lixuwei.xy@gmail.com>
 2026-04-13 21:22:00 -07:00
huangtingwei
e9d6b9eb2d [HiCache & HybridModel] mooncake backend support DSA & mamba model (#21259) 
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
Co-authored-by: pansicheng <sicheng.pan.chn@gmail.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
 2026-04-13 18:47:36 -07:00
ishandhanani
cc449ac4e5 feat(metrics): expose raw KV cache pool token counts as prometheus gauges (#22726) 2026-04-13 18:30:36 -07:00
huangtingwei
945d73824f [HiSparse] Clarify decode token usage logs (#22331) 2026-04-13 18:03:25 -07:00
yuki-brook
1ec018f27a [Feature] Add SiMM as sglang HiCache Storage backend (#18016) 2026-04-13 17:12:37 -07:00
Liangsheng Yin
33a3ba256f Delete dead rematch path in SessionAwareCache.release_session (#22735) 2026-04-13 17:02:40 -07:00
Lianmin Zheng
9fb00ede15 Clean up TokenizerManager and req_time_stats: reduce overhead and simplify (#21646) 2026-04-13 16:47:32 -07:00
Jia Guo
a2b5111962 perf: skip KV cache in FA backend for embedding mode (#21971) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-13 16:27:52 -07:00
Lianmin Zheng
8f9553bccb [Misc] Migrate SGLANG_SET_CPU_AFFINITY to envs and refactor model config building (#22730) 2026-04-13 16:10:31 -07:00
mqhc2020
f4f9e68189 [AMD] Add MoE weights and scales padding (#21097) 
Co-authored-by: HAI <hixiao@gmail.com>
 2026-04-13 15:50:15 -07:00
Yilong Zhao
b1efce342c env: add knob to control SWA eviction interval (#22645) 2026-04-13 15:37:59 -07:00
Lianmin Zheng
f81b6e8f51 [Misc] Add @cache_once to is_arch_support_pdl in jit_kernel (#22724) 2026-04-13 14:42:49 -07:00
Baizhou Zhang
b441317aa4 Revert "Upgrade CI default CUDA version from 12.9 to 13.0" (#22727) 2026-04-13 14:39:24 -07:00
Lianmin Zheng
ba7bcca6b3 Use reshape instead of contiguous().view() in TRTLLMHAAttnBackend (#22517) 2026-04-13 14:29:12 -07:00
Kurt Shuster
ff13dfee45 [lora][moe] Virtual experts for LoRA MoE (#22122) 
Co-authored-by: Yusheng Su <yushengsu.thu@gmail.com>
 2026-04-13 21:19:30 +00:00
ishandhanani
6b2bf66cd9 fix[glm4.7 flash]: properly detect gfx95_quant_format (#22720) 2026-04-13 13:10:07 -07:00
Asish Kumar
39810762d2 fix: use describe mode for SGLang version detection (#22600) 
Signed-off-by: Asish Kumar <officialasishkumar@gmail.com>
 2026-04-13 09:45:45 -07:00
DarkSharpness
314d6ecf08 [Feature][JIT Kernel] Fused TP QK norm For Minimax (#20673) 
Co-authored-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>
 2026-04-13 20:29:47 +08:00
Xiaole Guo
4df60434d7 [diffusion] model: support stable-diffusion-3-medium-diffusers (#19225) 
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
Co-authored-by: Kangrui Du <kangruidu@gmail.com>
Co-authored-by: Xiaole Guo <gxlvera@gmail.com>
 2026-04-13 16:07:06 +08:00
Chandrakant Khandelwal
1e9eecfa36 [Intel GPU] Enable sgl-kernel-xpu fused_experts MoE kernel path for GPT-OSS bf16 models. (#22417) 2026-04-13 13:45:48 +08:00
Mick
d524f110ac [diffusion] refactor: streamline denoising stages (#22633) 2026-04-13 13:34:37 +08:00
Polisetty V R K Jyothendra Varma
7d2c11970c [Intel GPU] Upgrade pytorch xpu version to 2.11 (#21908) 
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-04-13 13:16:24 +08:00
Zhangheng
5549d910c6 [hisparse]: Adding ci for hisparse kvcache-swap-in jit-kernel (#22155) 2026-04-13 12:50:29 +08:00
Zhangheng
305b42935a [HiSparse]: Add benchmark for hisparse kernel (#22187) 2026-04-13 12:49:18 +08:00
Alison Shao
3f4fbc165d Upgrade CI default CUDA version from 12.9 to 13.0 (#21441) 2026-04-12 21:48:40 -07:00
Mohammad Miadh Angkad
4dbd59850b Add bfloat16 KV cache validation for HiSparse (#22505) 2026-04-13 12:41:42 +08:00
Xiaoyu Zhang
fae0a2fc3c [codex] Add LTX-2.3 benchmark skill recipes (#22631) 2026-04-13 12:23:32 +08:00
Mick
bf022e177c Revert "[Diffusion] Add FLUX.1-dev ModelOpt NVFP4 support (#22574)" (#22649) 2026-04-13 11:17:32 +08:00
Zhangheng
bc59cc0f96 [RaidxTree Refactor]: Support Unified HybridRadixTree V2 (#21206) 
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: pansicheng <sicheng.pan.chn@gmail.com>
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: xiezhq-hermann <xiezhq@stanford.edu>
 2026-04-13 10:28:22 +08:00
Ziang Li
5593539942 [RL] Refactor NVFP4 shuffling/swizzling to in-place replacement (#22204) 2026-04-12 19:08:45 -07:00
blzheng
934e19a610 [CPU] Fix argument issues in qkv_proj_with_rope_fused_weight and bmm… (#21367) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-04-13 09:59:13 +08:00
Liangsheng Yin
da6b8e1448 Extract pause_resume_in_place kit; rename test_abort to test_scheduler_control (#22647) 2026-04-12 18:49:37 -07:00
Lawrence Wu
28e40d873c fix(PD): respect pause_generation in disagg event loops (#20908) 2026-04-12 18:07:51 -07:00
ishandhanani
c1ab68b45e fix: streaming session race condition + some metrics (#21875) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
 2026-04-12 18:05:23 -07:00
Xiaoyu Zhang
37fc47c645 diffusion: fix layerwise offload for ModelOpt quantized DiTs (#22594) 2026-04-13 08:01:54 +08:00
Xiaoyu Zhang
03a1a7b81c [Diffusion] Add FLUX.1-dev ModelOpt NVFP4 support (#22574) 2026-04-13 07:57:41 +08:00
Kurt Shuster
f81b6df3a3 [lora] Fix partial MoE rank loading, VL lm_head, strict loading, deepseek on-demand (#21864) 
Co-authored-by: Yusheng Su <yushengsu.thu@gmail.com>
 2026-04-12 16:25:02 -07:00
Khoa Pham
1f8df97054 Fix broken streaming response with --incremental-streaming-output (#22549) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-12 15:05:58 -07:00
Zhiyu
d4ad30b94c [diffusion] quant: enable modelopt quantized FLUX deployment (#20082) 
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-12 23:35:33 +08:00
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