EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity
5,977 Commits 8 Branches 0 Tags
cbac4997509f6a857655f7443de1a4833999f4e0
Commit Graph

3995 Commits

Author SHA1 Message Date
YanbingJiang
cbac499750 Split test_intel_amx_attention_backend.py to pass CI of timeout (#11370) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2025-10-15 19:22:32 -07:00
Shangming Cai
476c67d7fc Fix missing a2a backend init of GLM4.5 MoE Block (#11692) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2025-10-15 19:13:08 -07:00
Shangming Cai
868403f642 [PD] Add PD support for hybrid model (Qwen3-Next, DeepSeek V3.2 Exp) (#10912) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
Co-authored-by: ZeldaHuang <hzm414167@alibaba-inc.com>
 2025-10-15 18:59:14 -07:00
Hanming Lu
97d857c096 [Mamba] Increase default mamba_full_memory_ratio to 0.9 (#11679) 2025-10-16 09:56:43 +08:00
Lianmin Zheng
cd7e1bd591 Sync code and test CI; rename some env vars (#11686) 2025-10-15 18:37:03 -07:00
Huaiyu, Zheng
729b7edf72 enable rmsnorm on XPU (#10248) 2025-10-15 17:54:18 -07:00
DiweiSun
4c03dbaaef [CI][XPU]enable sglang CI on Intel XPU (#9493) 
Co-authored-by: huaiyuzh <huaiyu.zheng@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
 2025-10-15 17:13:19 -07:00
sglang-bot
baf277a9bf chore: bump SGLang version to 0.5.3.post2 (#11680) 
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
 2025-10-15 16:49:14 -07:00
Chang Su
f226d3da2a Fix missing json imports in serving_responses.py (#11681) 2025-10-15 13:01:55 -07:00
Chang Su
30ea4c462b [tool call] Fix prev_tool_call_arr management in base_format_detector.py (#11367) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2025-10-15 09:51:51 -07:00
Shangming Cai
6d0364681c Fix 1-step draft model forward (#11653) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2025-10-15 19:11:33 +08:00
Liangsheng Yin
8221f9ae8b Tiny cleanup some eagle unused codes (#11660) 2025-10-15 17:24:08 +08:00
Stefan He
6b143d62a2 Clean up some Qwen3-Next and deterministic code (#11585) 2025-10-15 15:19:37 +08:00
Zheng Wengang
b2c8566920 [BugFix][Qwen3-VL]: fix cu_seqlens in qwen3-vl (#11458) 2025-10-14 22:16:49 -07:00
Yineng Zhang
91fc5bb5a9 feat: add add_chunked_prefix_cache_attention_backend (#11636) 2025-10-14 21:48:13 -07:00
Lifu Huang
780fbf2f38 [Fix] Fix accuracy bug in CSGMV kernel caching key. (#11579) 2025-10-14 20:25:56 -07:00
Jinwu
825432fce6 [1/N]Support DeepSeek-R1 w4a8 normal deepep (#8247) 
Co-authored-by: Hank Han <hanhan7630@outlook.com>
 2025-10-14 20:10:53 -07:00
Xun Sun
a40229f6f8 [1/N] Introduce Mooncake Backend and Mooncake EP to Support Elastic EP (#10423) 
Co-authored-by: Hank Han <hanhan7630@outlook.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2025-10-14 19:40:54 -07:00
Sahithi Chigurupati
e9e120ac7a fix: upgrade transformers to 4.57.1 (#11628) 
Signed-off-by: Sahithi Chigurupati <chigurupati.sahithi@gmail.com>
Co-authored-by: zhyncs <me@zhyncs.com>
 2025-10-14 18:35:05 -07:00
cctry
1d7f783501 Refactor kv cache free (#11351) 2025-10-14 17:45:19 -07:00
Simo Lin
325951460f [router][grpc] add warm up to grpc server (#11627) 
Co-authored-by: Chang Su <chang.s.su@oracle.com>
 2025-10-14 16:11:16 -07:00
DarkSharpness
e28c9e526f [Minor] Update xgrammar dependency (#11622) 2025-10-14 13:46:50 -07:00
Lianmin Zheng
b98cf39866 [Auto Sync] Update collector.py (20251014) (#11625) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
 2025-10-14 13:34:33 -07:00
Lianmin Zheng
27d710457c [Auto Sync] Update scheduler.py, server_args.py (20251014) (#11623) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
 2025-10-14 13:20:03 -07:00
Baizhou Zhang
c224a4c6cc Fix log for chunked prefix cache (#11624) 2025-10-14 11:49:33 -07:00
strgrb
94d26d850d use non_blocking h2d in ForwardBatch.prepare_mlp_sync_batch. (#11605) 2025-10-14 11:30:59 -07:00
Liangsheng Yin
5ea96ac7cc Reduce one step decode for draft model. (#11561) 2025-10-14 23:52:04 +08:00
yinghui
56222658ec move eagle draft post process to cuda graph (#11434) 
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
 2025-10-14 22:50:53 +08:00
Alex Chi Z
dc965db0e0 make radix cache deterministic (#10721) 
Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
 2025-10-14 21:01:52 +08:00
Scott Lee
817e46f412 Refactor spec decoding metrics calculation into separate TokenizerManager utility function (#11586) 2025-10-14 20:45:49 +08:00
Liangsheng Yin
5a33c3aae7 Optimize Triton Draft Backend (#11556) 2025-10-14 20:08:32 +08:00
Qiaolin Yu
e4358a4585 Add fused_moe_triton config: triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200.json (#11587) 2025-10-14 13:24:43 +08:00
Lianmin Zheng
ba2ce28fe9 [Auto Sync] Update model_config.py (20251014) (#11580) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
 2025-10-13 22:16:34 -07:00
Chenxi Li
28f80b1244 Implement LRU eviction policy for LoRA adapters (#11041) 2025-10-13 20:18:25 -07:00
Xiaoyu Zhang
88a6f9dab5 bench_serving support PD Disaggregation (#11542) 2025-10-13 19:43:26 -07:00
fzyzcjy
cb8ed2c09a Make DeepEP combine recv do not overlap (#11535) 2025-10-13 18:40:42 -07:00
Trevor Morris
384733639a [DSv32] Use torch.compile for _get_logits_head_gate (#11565) 2025-10-13 18:38:39 -07:00
Neelabh Sinha
aaf7af1b17 [FEATURE] Add Profile Trace Merger for Distributed Traces (#11413) 2025-10-14 09:20:17 +08:00
Yuwei An
932e263725 Compilation Folder Reset (#11539) 
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
 2025-10-14 09:19:12 +08:00
Qiaolin Yu
43f80884c5 Fix accept rate in speculative decoding metrics (#11572) 2025-10-13 16:35:50 -07:00
Chang Su
887c2b4575 [router][grpc] Add serve_grpc to launch_server and log id for HealthCheck (#11564) 2025-10-13 16:07:19 -07:00
fzyzcjy
065ce81574 Tiny cleanup fp4 gemm calls (#11537) 2025-10-13 14:48:22 -07:00
Johnny
cb8f3d90d3 [NVIDIA] update pyproject.toml to support cu130 option (#11521) 2025-10-13 13:03:31 -07:00
Trevor Morris
c9cff2b984 Fix DeepSeek-v3.2 default config (ValueError: not enough values to unpack (expected 4, got 3)) (#11557) 2025-10-13 11:27:40 -07:00
Scott Lee
b6fb5d7666 Add metrics for speculative decoding (acceptance rate, average acceptance length) (#11441) 2025-10-13 11:24:27 -07:00
Lianmin Zheng
5e3f7e7fa9 Minor: improve sampler & remove unused fields from model_config.py (#11531) 2025-10-13 11:04:44 -07:00
Liangsheng Yin
acc2327bbd Move deep gemm related arguments to sglang.srt.environ (#11547) 2025-10-14 00:34:35 +08:00
Liangsheng Yin
bfadb5ea5f Adjust overlap event loop (#11507) 2025-10-14 00:33:19 +08:00
ai-jz
9cc1e065f1 [router][Fix] Include grpc reflection runtime dependency (#11419) 
Co-authored-by: Chang Su <chang.s.su@oracle.com>
 2025-10-13 09:32:42 -07:00
Mick
f35f120d70 fix: fix video input for qwen3-vl (#11442) 2025-10-13 09:30:43 -07:00