minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
11,649 Commits 2 Branches 0 Tags
39c6bf730c417de5776439ad8fc83f7be92ad75e
Commit Graph
11649 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Michael 39c6bf730c [AMD][CI] Add GLM-5-MXFP4 accuracy and perf nightly tests for MI35x (#21773) 2026-04-14 18:55:36 -07:00
Lianmin Zheng adb310b976 Cleanup server_args.py and minor code tidying (#22820) 2026-04-14 18:52:41 -07:00
Chen, ZhentaoChen, Toddjacky.cheng
 		ea05ea5abe [AMD] Enable share expert fusion with router experts for Qwen3.5 BF16 & FP8 (#20736) 
Co-authored-by: Chen, Todd <zhenchen@amd.com>
Co-authored-by: jacky.cheng <yichiche@amd.com>
 2026-04-14 18:52:36 -07:00
Piotr Mazurek 46c8a597ef [VLM] fix LFM2-VL offline inference and GPU JPEG decode (#22448) 2026-04-15 09:13:25 +08:00
ishandhanani 2c9e76d333 ci: skip approval for nightly gb200 runs, keep for manual triggers (#22768) 2026-04-14 16:34:57 -07:00
Alexis MacAskill e15401ee0e Add runai-model-streamer into Python packages installed in Dockerfile and fix NotADirectoryError Docker regression (#22537) 2026-04-14 16:25:41 -07:00
Lianmin Zheng 222eda1598 [Misc] Use cache_once for is_arch_support_pdl in sgl-kernel (#22725) 2026-04-14 15:22:10 -07:00
Jimmy Shong e83560562b Update CI Permissions (#22826) 2026-04-14 15:13:31 -07:00
Alex NailsClaude Opus 4.6gemini-code-assist[bot]
 		8092431316 [serving] replace O(n²) stream_buffer string concat with integer offset (#22606) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-04-14 14:48:44 -07:00
Liangsheng Yin 36891ab514 Rename _alive_streaming_session_count; use _is_streaming helper (#22755) 2026-04-14 13:26:03 -07:00
Liangsheng Yin 0cb7295698 Fix streaming session busy-check double-counting via active_pool_idxs (#22753) 2026-04-14 13:11:06 -07:00
mingyue300 b4616dcbf5 [BugFix] Fix EAGLE speculative decoding missing grammar-based finish … (#21723) 2026-04-14 12:43:50 -07:00
MickandClaude Opus 4.6 d2f479e544 [diffusion] chore: auto-enable best parallel setting if unspecified (#22763) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-15 00:02:05 +08:00
Ke Bao 3c0a6c6987 Add page_size and SWA coverage to unified radix cache bench test (#22815) 2026-04-14 23:58:05 +08:00
Bi Xue 070c6a2489 [sgl] perf optimization for eplb (#21232) 2026-04-14 22:52:17 +08:00
Ke Bao 9f9e0231bb Refactor unified radix cache UT into parameterized test suite (#22812) 2026-04-14 22:34:33 +08:00
Mick c5e95080d2 [diffusion] model: support Ltx 2.3 two stage ti2v (#22667) 2026-04-14 22:10:08 +08:00
chx96642264 680bd4b429 [NPU] Modify the parameter name and optional values, and add the parameter restrictions. Modify some parameters supported type. (#22804) 2026-04-14 21:34:07 +08:00
McZyWuandroot 1588856e9b [NPU] qwen3next low latency best practice docs. (#22808) 
Co-authored-by: root <root@localhost.localdomain>
 2026-04-14 21:21:37 +08:00
amote-i ddc7daaf89 [NPU] [DOC] Update NPU docs to match latest code (#22796) 2026-04-14 21:10:28 +08:00
lawtherWu 454228e071 hicache storage backend mooncake support ascend hixl (#20016) 2026-04-14 20:51:06 +08:00
loading66 074c2a476d fix:[NPU]correct the full name of then Kimi model (#22799) 2026-04-14 20:15:22 +08:00
jianzhao-xuandJianzhao Xu 68dfffaaa3 Offloading docs update (#22795) 
Co-authored-by: Jianzhao Xu <xujianchao@huawei.com>
 2026-04-14 20:03:29 +08:00
xdtbynd 88253c39b0 [Docs] Fix formatting of tool-call-parser options (#22793) 2026-04-14 19:21:31 +08:00
amote-i 368cdfbe2f [NPU] [DOC] Fix outdated descriptions in the NPU documentation (#22707) 2026-04-14 19:21:15 +08:00
Jia GuoandClaude Opus 4.6 6da3aba6a5 perf: optimize PCG inductor path for FP8 models (#21734) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-14 17:51:27 +08:00
xutizhou 3cb3f7c018 fix: EPLB dispatch OOB when shared experts fusion enabled under DeepEP (#22525) 2026-04-14 02:33:27 -07:00
Jincong Chen 6760c790bd [bugfix] avoid attention padding tokens computation in pcg (#17706) 2026-04-14 16:08:23 +08:00
MichaelandHaiShaw eab045b2b7 [AMD] Add MiniMax-M2.7 accuracy and performance nightly tests (#22722) 
Co-authored-by: HaiShaw <hixiao@gmail.com>
 2026-04-14 00:30:11 -07:00
xiaobochen-amdandkk d7ecab5113 [ROCm]fix(aiter): cast fp8 prefill output back to model dtype (#22626) 
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
 2026-04-14 00:25:09 -07:00
Xiaoyu Zhang f97c608caa [diffusion] quant: add FLUX.1-dev modelopt nvfp4 support (#22672) 2026-04-14 15:00:59 +08:00
Sahithi Chigurupatiandishandhanani 7c1bde2e38 [CI] Add optional image input to GB200 nightly workflow_dispatch (#22745) 
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
 2026-04-13 23:57:15 -07:00
Colin ZandHAI b10f852118 GLM-5/5.1 MXFP4 Checkpoint Inference Compatibility Fix (#22543) 
Co-authored-by: HAI <hixiao@gmail.com>
 2026-04-13 23:56:48 -07:00
Baizhou ZhangandClaude Opus 4.6 8fe9bbffb6 [CI] Reinstall flashinfer-jit-cache on CUDA version mismatch (#22741) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 23:04:23 -07:00
YC Yen-Ching Tsengandbingxche d44eb16ac6 [AMD] Replace push trigger with scheduled runs and enable parallel stage execution (#22489) 
Co-authored-by: bingxche <bingxche@amd.com>
 2026-04-14 13:33:29 +08:00
YAMY 657945c338 Replace all-reduce + dp_scatter with reduce_scatterv for DP attention (#22642) 2026-04-13 21:51:10 -07:00
ishandhanani 520ce526b9 Restore Qwen3 rope config fallback (#22739) 2026-04-13 21:47:37 -07:00
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
Jia GuoandClaude Opus 4.6 bc16130a17 ci: skip full rerun when sgl-kernel wheel already built (#22534) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-13 20:32:55 -07:00
huangtingweihzh0425pansichengispobockVladislav Nosivskoy
 		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
Zhai Feiyue c456cba7fd [gateway] Support SGLANG_LOG_MS for millisecond precision in router logs (#22506) 2026-04-13 17:28:00 -07:00
yuki-brook 1ec018f27a [Feature] Add SiMM as sglang HiCache Storage backend (#18016) 2026-04-13 17:12:37 -07:00
Sahithi Chigurupati ff61b2e470 [CI] Add workflow_dispatch and environment gate to GB200 nightly pipeline (#22733) 2026-04-13 17:08:18 -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 GuoandClaude Opus 4.6 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
mqhc2020andHAI f4f9e68189 [AMD] Add MoE weights and scales padding (#21097) 
Co-authored-by: HAI <hixiao@gmail.com>
 2026-04-13 15:50:15 -07:00