Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• ea96106000 [Feature] Sglang Tracing: Fine-Grained Tracking for Request Latency - Part 2 (#10804) Feng Su 2025-10-28 16:25:46 +08:00
• b1e13e7cea [hotfix] Incorrect CombineOverlapArgs in SBO (#12230) Cheng Wan 2025-10-28 01:23:06 -07:00
• cc7b04a29c Feature/Add GET endpoint to query loaded LoRA adapters (#12229) Chenxi Li 2025-10-28 01:22:00 -07:00
• d85d6dba3b [router] configure workflow retries and timeout based on routerConfig (#12252) Simo Lin 2025-10-28 00:41:20 -07:00
• c5642a7a7a [router] use mcp struct from sdk and clean up code across codebase (#12249) Simo Lin 2025-10-28 00:33:10 -07:00
• 691c8534cf Support releasing CUDA graph memory when paused (#7873) 3 people 2025-10-28 14:40:50 +08:00
• d2b8c4123e Opt fused triton moe: add tma for down proj kernel (#10567) Yongfei Xuandybyang 2025-10-28 14:26:17 +08:00
• bf8f7a944f Add per-request retraction count (#11177) Scott Lee 2025-10-27 23:22:34 -07:00
• 81a632ace6 [DeepseekV32] Enable flashmla_prefill kernel with fp8 kvcache (#11655) hlu1 2025-10-27 23:11:48 -07:00
• 83b2240074 [router] remove code duplication (#12245) Simo Lin 2025-10-27 23:01:44 -07:00
• 285a8e6986 docker: add CUDA13 support in dockerfile and update GDRCopy/NVSHMEM for blackwell support (#11517) ishandhananiandBaizhou Zhang 2025-10-27 22:00:54 -07:00
• 813bd6f85c [2/2] Use moe_sum_reduce cuda kernel (#10654) 3 people 2025-10-28 12:01:57 +08:00
• 729f612dc6 Update openai package version to 2.6.1 (#12222) Xinyuan Tong 2025-10-27 20:23:40 -07:00
• 899453ac50 Use explicit uint64 dtype for Tensor data_ptr() to avoid overflow (#11994) jianan-gu 2025-10-28 10:05:57 +08:00
• ce832d7034 Add env var to control custom Triton kernel cache and set CSGMV as default backend. (#12176) Lifu Huang 2025-10-27 17:49:32 -07:00
• 88596739a4 Support running FP4 Deepseek on SM120. (#11708) weiliang 2025-10-28 08:37:49 +08:00
• a6ea3add76 [Auto Sync] Update scheduler.py, spec_info.py, run_suite.py... (20251027) (#12235) 3 people 2025-10-27 17:21:08 -07:00
• 326c84c493 Compiling rope while preserving true on policy (#12161) fzyzcjy 2025-10-28 08:02:17 +08:00
• 8da608cce0 fix: AttributeError: 'NixlKVManager' object has no attribute 'prefill_tp_size_table' (#12234) gongwei-130 2025-10-27 15:57:33 -07:00
• 9fc3e8aac7 Add support for Matryoshka embeddings (#126) (#11142) satyamk7054andSatyam Kumar 2025-10-27 11:49:36 -07:00
• c11b34d599 rope xpu: fix missing argument 'fused_set_kv_buffer_arg' and replace native with sgl_kernel_xpu impl (#12006) Chunyuan WU 2025-10-28 01:02:18 +08:00
• 05ad28f25e [Feature] PD-Multiplexing Context and Scheduler. (#11592) ykcombat 2025-10-28 00:54:43 +08:00
• 0cae873fcd check_offload_progress more frequently (#11656) pansicheng 2025-10-28 00:37:38 +08:00
• a8b91f6b2d improve mimax-m2 rmsnorm precision (#12186) Haichao Zhu 2025-10-28 00:01:42 +08:00
• 959d1ab84b fix(metrics): double times add_latency for DECODE_BOOTSTRAP (#12209) Jimmy 2025-10-27 23:59:48 +08:00
• 6c1c193308 [Detokenizer Manager] Cleanup state when reqs are finished (#12205) Muqi Li 2025-10-27 23:59:09 +08:00
• 3029d30189 Fix crash after flush cache (#12107) cctryandfzyzcjy 2025-10-27 08:52:27 -07:00
• f389f01714 Optimize triton_mrope with torch compile (#12112) Yuan Luoandluoyuan.luo 2025-10-27 23:49:22 +08:00
• caa4819bfc Add support for AutoRound quantized models (#10153) Weiwei 2025-10-27 18:17:29 +08:00
• a88b006ecf GLM-4-0414 and GLM-4.1V Code Refactor (#12117) Yuxuan Zhang 2025-10-27 16:57:07 +08:00
• ce112c07fe [sgl-kernel][4/N]Support Expert Specialization Grouped GEMM (#12080) Qi Yuhang 2025-10-27 16:20:01 +08:00
• f7dc2f334b [sgl-kernel] feat: Support sm120 cutlass fp8 gemm kernel (#9403) Joonchen Liau 2025-10-27 14:45:45 +08:00
• cd784faf20 docs: update contact (#12192) Yineng Zhang 2025-10-26 23:23:39 -07:00
• 75c09e1ffe [Fix] Fix cu130 sgl-kernel wheel renaming (#12173) Baizhou Zhang 2025-10-26 22:44:05 -07:00
• 09af0a7b5a [sgl-route] Optimize the use of constant slices and retain to simplif… (#12159) rongfu.leng 2025-10-27 12:14:33 +08:00
• c8d385ce68 [doc] add example of using w4fp8 for Deepseek (#12057) Kevin_XiongandChao Xiong 2025-10-27 11:10:38 +08:00
• 55d75e11bd chore: bump SGLang version to 0.5.4.post1 (#12169) sglang-bot 2025-10-27 09:35:20 +08:00
• 3f4cc0aff0 Remove description for --enable-beta-spec argument (#12177) Xinyuan Tong 2025-10-26 16:49:39 -07:00
• cadfae666d fix broken deepep/flashmla install in container by adding --no-build-isolation (#12170) ishandhanani 2025-10-26 16:39:51 -07:00
• da1766e444 Remove deprecated --enable-beta-spec argument and fix b200 test (#12167) Kangyan-ZhouandClaude 2025-10-26 15:54:40 -07:00
• a124b517f6 [router] Remove SharedXxxStorage type aliases to make Arc explicit (#12171) Chang Su 2025-10-26 14:48:07 -07:00
• d05a968ba8 [router][grpc] Add ResponsesContext and fix error propagation in responses api (#12164) Chang Su 2025-10-26 14:07:19 -07:00
• 94aad0de99 [misc][grpc] Remove duplicate log (#12168) Chang Su 2025-10-26 14:06:59 -07:00
• 7ebc28f5d6 [WIP] support MiniMax M2 model (#12129) 5 people 2025-10-26 13:58:54 -07:00
• b89111d69b add gitignore for claude code and serena mcp (#12166) Simo Lin 2025-10-26 13:30:17 -07:00
• 0b3b3e9a69 transfer mrope_position_delta to device when first running (#11047) ash-sigh 2025-10-27 04:06:09 +08:00
• a1d5bc4cce Avoid using flashinfer_allreduce_fusion when dp attention is enabled. (#11632) Elfie Guo 2025-10-26 12:31:14 -07:00
• a8023891f6 model: support NVILA and NVILA Lite (#10399) Zijian Zhang 2025-10-27 00:58:09 +08:00
• 0103f374ba Support DeepGEMM for deterministic inference (#12142) fzyzcjy 2025-10-26 22:36:17 +08:00
• 96a5a949f6 [Fix] fix allreduce bug in Piecewise Graph (#12106) zyksir 2025-10-26 21:15:48 +08:00
• ea385ae85a Fix ITL metrics when using openai endpoint with spec (#12156) Liangsheng Yin 2025-10-26 18:06:25 +08:00
• 9e949e5877 [router] centralize mcp tool args handling (#12155) Simo Lin 2025-10-26 01:47:12 -07:00
• 6dbb569bc3 [router][grpc] Fix tool call id in parse_json_schema_response (#12152) Chang Su 2025-10-26 01:40:53 -07:00
• 5994e6c373 Do not use MagicMock to mock server_args in tests (#12154) Liangsheng Yin 2025-10-26 16:00:46 +08:00
• 3e6281d0aa [HiCache]Page head layout IO kernel (#11615) huangtingwei 2025-10-26 15:53:50 +08:00
• 6371f7af27 [quantization] AWQ Marlin doesn't work when dtype is bfloat16 (#11494) Kai-Hsun ChenandXinyuan Tong 2025-10-26 00:49:45 -07:00
• 8491c794ad [misc] depdencies & enviroment flag (#12113) Liangsheng Yin 2025-10-26 14:52:35 +08:00
• bda3758fac [log] Make forward iter count optional (#12116) Liangsheng Yin 2025-10-26 14:51:07 +08:00
• 7b36c47b3b Clean up attention backend selection code & Other minor rename (#12136) Lianmin Zheng 2025-10-25 23:50:12 -07:00
• 773d89da8c [router] cleaned up all the redundant comments in the config module (#12147) Chang Su 2025-10-25 23:10:59 -07:00
• 03e7d94916 [router] update smg code owners for each component (#12141) Simo Lin 2025-10-25 22:28:59 -07:00
• ff60406429 [NVIDIA] Change default quant method for model_opt (#11991) Kaixi Hou 2025-10-25 22:04:57 -07:00
• 212f5e4822 [router] MCP Manager Refactoring - Flat Architecture with Connection Pooling (#12097) Simo Lin 2025-10-25 21:26:28 -07:00
• fe527812a6 docs: update README (#12139) Yineng Zhang 2025-10-25 20:49:10 -07:00
• 97828878d8 [Doc] Small update of DeepSeek v3.2 document (#12138) Baizhou Zhang 2025-10-25 20:34:05 -07:00
• c001deba37 Make bmm batch invariant injection optional (#12118) fzyzcjy 2025-10-26 10:18:35 +08:00
• b4d2da106e [docs] upd docker files names everywhere (#12133) Vincent Zhong 2025-10-25 21:20:23 -04:00
• b72f9f08c1 [Test] Add dsv3.2 nsa backend testing (#11936) Johnsonms 2025-10-25 17:07:37 -07:00
• 8e70064c37 Clean up server launch code and multi tokenizer (#12132) Lianmin Zheng 2025-10-25 16:40:27 -07:00
• d98b81e260 Accelerate deepseek fp4 b200 ci (#11993) Qiaolin Yu 2025-10-25 15:29:14 -07:00
• bcecf27e7c [Doc] Fix format for deepseek v3.2 document (#12130) Baizhou Zhang 2025-10-25 15:07:50 -07:00
• 4b0ac1d52a Update sgl-kernel version to 0.3.16.post4 (#12125) Baizhou Zhang 2025-10-25 14:33:33 -07:00
• 8e987fa2a3 Update document index for DeepSeek-v32 docs (#12101) Baizhou Zhang 2025-10-25 13:38:58 -07:00
• 9e656dd3b2 Reenable b200 tests (#11814) Kangyan-Zhou 2025-10-25 13:02:33 -07:00
• 3862661cd4 Fix token for CI monitor (#12127) Lianmin Zhengandsglang-bot 2025-10-25 12:38:26 -07:00
• c8492978a1 Fix Illegal Instruction/IMA errors when using DP attention -- num_tokens_for_logprob calculation (#12115) YAMY 2025-10-25 12:28:26 -07:00
• 428710c2ec clean up github tokens (#12126) Lianmin Zhengandsglang-bot 2025-10-25 12:23:54 -07:00
• d9b31011aa Skip TestLlama4LoRA in CI (#12098) Lifu Huang 2025-10-25 12:16:36 -07:00
• d0cff78f54 [CI] Add ci monitor balance workflow (#11962) Xiaoyu Zhang 2025-10-26 03:14:36 +08:00
• e8b71445c0 [Misc] Improve the error message of failed import (#12119) DarkSharpness 2025-10-26 03:09:05 +08:00
• 4caca1ba04 Clean up server args & Add CI scripts (#12124) Lianmin Zheng 2025-10-25 11:53:57 -07:00
• ceb105a780 Update setup_github_runner.md Kangyan-Zhou 2025-10-25 09:22:00 -07:00
• 22cbc9c086 [bugs] docker file name should be <name>.Dockerfile so it can properly render (#11869) Simo Lin 2025-10-25 08:34:43 -07:00
• 3865afc5df fix: release workflow should work on both archs (#12110) ishandhanani 2025-10-24 23:22:31 -07:00
• 4ea42f7cea [router] Refactor data connector architecture with unified storage modules (#12096) Keyang Ru 2025-10-24 22:44:34 -07:00
• ea13cb1452 [Auto Sync] Update test_deterministic.py, test_deterministi... (20251024) (#12083) 3 people 2025-10-24 22:28:01 -07:00
• a04212f128 chore: bump sgl-kernel version to 0.3.16.post4 (#12103) sglang-botandsglang-bot 2025-10-25 13:04:14 +08:00
• ce86979355 [Fix] Set global args in cpu test (#12105) Baizhou Zhang 2025-10-24 21:46:17 -07:00
• 22f55e1b15 Fix kernel version bump file (#12087) Kangyan-Zhou 2025-10-24 20:32:33 -07:00
• 8982418957 Fix 'KeyError' for per_token expert distribution recorder (#9501) vipwangerxiaoandPeng Wang 2025-10-25 11:28:50 +08:00
• 433c622e80 [Docs] update sgl-kernel readme (#11379) Fan Yin 2025-10-25 10:31:14 +08:00
• 20bd2271e2 Support true on-policy (#12058) fzyzcjy 2025-10-25 10:23:42 +08:00
• 649949807f [10/N] MoE Refactor: reorganize deepgemm runner in DeepEPMoE (#12054) Cheng Wan 2025-10-24 19:16:17 -07:00
• 729b242934 [Doc] Add documentation for DeepSeek V3.2 (#11877) 3 people 2025-10-24 19:06:22 -07:00
• d7056c5236 Enhance tests in deterministic kernels (#12070) fzyzcjy 2025-10-25 08:53:22 +08:00
• 13bf565d60 [2/N]Support DeepSeek-R1 w4a8 low latency deepep (#8464) 3 people 2025-10-25 08:41:16 +08:00
• e51046beaa perf: trtllm_mla attention backend spec decoding speedup w/ cuda graph (#12093) yinghui 2025-10-24 16:05:44 -07:00
• 4eeeae1e75 Fix: Update blog link (#12071) Luca Lowndes 2025-10-25 09:26:23 +11:00
• f4b78d137c [1/2] deepseek deterministic: support deterministic inference for deepseek arch models on a single GPU (#12000) Minglei Zhu 2025-10-24 15:17:28 -07:00
• 4463e90dd2 [router][grpc] Remove gpt_oss parsers and remove _parser suffix in tool parser files (#12091) Chang Su 2025-10-24 15:14:41 -07:00