Commit Graph

9885 Commits

Author SHA1 Message Date
Muqi Li
6c1c193308 [Detokenizer Manager] Cleanup state when reqs are finished (#12205) 2025-10-27 23:59:09 +08:00
cctry
3029d30189 Fix crash after flush cache (#12107)
Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
2025-10-27 23:52:27 +08:00
Yuan Luo
f389f01714 Optimize triton_mrope with torch compile (#12112)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-10-27 23:49:22 +08:00
Weiwei
caa4819bfc Add support for AutoRound quantized models (#10153) 2025-10-27 18:17:29 +08:00
Yuxuan Zhang
a88b006ecf GLM-4-0414 and GLM-4.1V Code Refactor (#12117) 2025-10-27 16:57:07 +08:00
Qi Yuhang
ce112c07fe [sgl-kernel][4/N]Support Expert Specialization Grouped GEMM (#12080) 2025-10-27 01:20:01 -07:00
Joonchen Liau
f7dc2f334b [sgl-kernel] feat: Support sm120 cutlass fp8 gemm kernel (#9403) 2025-10-26 23:45:45 -07:00
Yineng Zhang
cd784faf20 docs: update contact (#12192) 2025-10-26 23:23:39 -07:00
Baizhou Zhang
75c09e1ffe [Fix] Fix cu130 sgl-kernel wheel renaming (#12173) 2025-10-26 22:44:05 -07:00
rongfu.leng
09af0a7b5a [sgl-route] Optimize the use of constant slices and retain to simplif… (#12159)
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
2025-10-26 21:14:33 -07:00
Kevin_Xiong
c8d385ce68 [doc] add example of using w4fp8 for Deepseek (#12057)
Co-authored-by: Chao Xiong <chaoxiong@Chaos-MacBook-Air.local>
2025-10-26 20:10:38 -07:00
sglang-bot
55d75e11bd chore: bump SGLang version to 0.5.4.post1 (#12169) 2025-10-27 09:35:20 +08:00
Xinyuan Tong
3f4cc0aff0 Remove description for --enable-beta-spec argument (#12177) 2025-10-26 16:49:39 -07:00
ishandhanani
cadfae666d fix broken deepep/flashmla install in container by adding --no-build-isolation (#12170) 2025-10-26 16:39:51 -07:00
Kangyan-Zhou
da1766e444 Remove deprecated --enable-beta-spec argument and fix b200 test (#12167)
Co-authored-by: Claude <noreply@anthropic.com>
2025-10-26 15:54:40 -07:00
Chang Su
a124b517f6 [router] Remove SharedXxxStorage type aliases to make Arc explicit (#12171) 2025-10-26 14:48:07 -07:00
Chang Su
d05a968ba8 [router][grpc] Add ResponsesContext and fix error propagation in responses api (#12164) 2025-10-26 14:07:19 -07:00
Chang Su
94aad0de99 [misc][grpc] Remove duplicate log (#12168) 2025-10-26 14:06:59 -07:00
赵晨阳
7ebc28f5d6 [WIP] support MiniMax M2 model (#12129)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Roger Young <42564206+rogeryoungh@users.noreply.github.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
2025-10-26 13:58:54 -07:00
Simo Lin
b89111d69b add gitignore for claude code and serena mcp (#12166) 2025-10-26 13:30:17 -07:00
ash-sigh
0b3b3e9a69 transfer mrope_position_delta to device when first running (#11047) 2025-10-26 13:06:09 -07:00
Elfie Guo
a1d5bc4cce Avoid using flashinfer_allreduce_fusion when dp attention is enabled. (#11632) 2025-10-26 12:31:14 -07:00
Zijian Zhang
a8023891f6 model: support NVILA and NVILA Lite (#10399) 2025-10-26 09:58:09 -07:00
fzyzcjy
0103f374ba Support DeepGEMM for deterministic inference (#12142) 2025-10-26 22:36:17 +08:00
zyksir
96a5a949f6 [Fix] fix allreduce bug in Piecewise Graph (#12106) 2025-10-26 21:15:48 +08:00
Liangsheng Yin
ea385ae85a Fix ITL metrics when using openai endpoint with spec (#12156) 2025-10-26 18:06:25 +08:00
Simo Lin
9e949e5877 [router] centralize mcp tool args handling (#12155) 2025-10-26 01:47:12 -07:00
Chang Su
6dbb569bc3 [router][grpc] Fix tool call id in parse_json_schema_response (#12152) 2025-10-26 01:40:53 -07:00
Liangsheng Yin
5994e6c373 Do not use MagicMock to mock server_args in tests (#12154) 2025-10-26 16:00:46 +08:00
huangtingwei
3e6281d0aa [HiCache]Page head layout IO kernel (#11615) 2025-10-26 15:53:50 +08:00
Kai-Hsun Chen
6371f7af27 [quantization] AWQ Marlin doesn't work when dtype is bfloat16 (#11494)
Signed-off-by: Kai-Hsun Chen <khchen@x.ai>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-10-26 15:49:45 +08:00
Liangsheng Yin
8491c794ad [misc] depdencies & enviroment flag (#12113) 2025-10-26 14:52:35 +08:00
Liangsheng Yin
bda3758fac [log] Make forward iter count optional (#12116) 2025-10-26 14:51:07 +08:00
Lianmin Zheng
7b36c47b3b Clean up attention backend selection code & Other minor rename (#12136) 2025-10-25 23:50:12 -07:00
Chang Su
773d89da8c [router] cleaned up all the redundant comments in the config module (#12147) 2025-10-25 23:10:59 -07:00
Simo Lin
03e7d94916 [router] update smg code owners for each component (#12141) 2025-10-25 22:28:59 -07:00
Kaixi Hou
ff60406429 [NVIDIA] Change default quant method for model_opt (#11991) 2025-10-25 22:04:57 -07:00
Simo Lin
212f5e4822 [router] MCP Manager Refactoring - Flat Architecture with Connection Pooling (#12097) 2025-10-25 21:26:28 -07:00
Yineng Zhang
fe527812a6 docs: update README (#12139) 2025-10-25 20:49:10 -07:00
Baizhou Zhang
97828878d8 [Doc] Small update of DeepSeek v3.2 document (#12138) 2025-10-25 20:34:05 -07:00
fzyzcjy
c001deba37 Make bmm batch invariant injection optional (#12118) 2025-10-26 10:18:35 +08:00
Vincent Zhong
b4d2da106e [docs] upd docker files names everywhere (#12133) 2025-10-25 18:20:23 -07:00
Johnsonms
b72f9f08c1 [Test] Add dsv3.2 nsa backend testing (#11936) 2025-10-25 17:07:37 -07:00
Lianmin Zheng
8e70064c37 Clean up server launch code and multi tokenizer (#12132) 2025-10-25 16:40:27 -07:00
Qiaolin Yu
d98b81e260 Accelerate deepseek fp4 b200 ci (#11993) 2025-10-25 15:29:14 -07:00
Baizhou Zhang
bcecf27e7c [Doc] Fix format for deepseek v3.2 document (#12130) 2025-10-25 15:07:50 -07:00
Baizhou Zhang
4b0ac1d52a Update sgl-kernel version to 0.3.16.post4 (#12125) 2025-10-25 14:33:33 -07:00
Baizhou Zhang
8e987fa2a3 Update document index for DeepSeek-v32 docs (#12101) 2025-10-25 13:38:58 -07:00
Kangyan-Zhou
9e656dd3b2 Reenable b200 tests (#11814) 2025-10-25 13:02:33 -07:00
Lianmin Zheng
3862661cd4 Fix token for CI monitor (#12127)
Co-authored-by: sglang-bot <sglangbot@gmail.com>
2025-10-25 12:38:26 -07:00