Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• d1be60c3c5 [Refactor] rename set_index_k_and_scale_buffer to set_index_k_scale_b… (#12956) Edwin Gao 2025-11-09 23:35:19 -05:00
• 583bb1804e [Docs] Add docs for Qwen3-VL image and video support (#12554) Adarsh Shirawalmath 2025-11-10 09:46:04 +05:30
• 1f2a6c691b Bugfix: LMCache Connector with Sglang (#12946) MMuzzammil1 2025-11-10 13:13:37 +09:00
• 61c7fe7aed Minor code cleanup / improvement for PREBUILT_EXTEND mode (#12948) Liangsheng Yin 2025-11-10 11:59:54 +08:00
• 83f89cc615 diffusion: skip full CI suite for multimodal_gen changes (#12940) Mick 2025-11-10 10:46:24 +08:00
• db24d34603 Support piecewise cuda graph for MLA (#11812) Ke Bao 2025-11-10 09:13:48 +08:00
• 885cfca273 ci: try to fix gpg error during kernel build (#12928) ishandhanani 2025-11-09 11:45:29 -08:00
• 4e916f9840 [lint] tiny fix unimported packages. (#12927) Liangsheng Yin 2025-11-10 00:59:10 +08:00
• 4f65a64666 Refactor / Unify event loop across PD-Disagg, Overlap, DP-Attn cases (#12839) Liangsheng Yin 2025-11-10 00:42:50 +08:00
• f5b3ccd9a5 feat: basic support for server-level multimodal cache (#10775) Mick 2025-11-10 00:27:50 +08:00
• bb00e24f87 Adjust server launch time in ci (#12917) Ke Bao 2025-11-09 20:41:29 +08:00
• 210a9cab6d [CI] Fix matrix.part in pr-test. (#12920) Liangsheng Yin 2025-11-09 18:53:18 +08:00
• b8ac4fcb51 [PD] feat: refactor custom mem pool and add barex pd support (#12332) Teng Ma 2025-11-09 18:51:34 +08:00
• 877cb52840 [CI] increase ut buckets & adjust estimation time. (#12919) Liangsheng Yin 2025-11-09 18:17:50 +08:00
• 3633f8b0cf Add Jet-Nemotron (#12448) Zijian Zhang 2025-11-09 17:32:47 +08:00
• 93cf60fc64 Fix Deepseek nightly tests (#12906) Kangyan-Zhou 2025-11-09 00:26:06 -08:00
• b5e0417392 Add kimi k2 thinking to ci (#12907) Ke Bao 2025-11-09 16:10:32 +08:00
• 8a821af793 fallback to triton mm_persistent kernel when deepGemm fail (#12911) Minglei Zhu 2025-11-08 23:42:26 -08:00
• 4b1d163bfd Add HF cleanup logic in ci_install_dependency.sh (#12895) Kangyan-Zhou 2025-11-08 22:56:25 -08:00
• c21a3ec299 Fix duplicate nightly test name (#12905) Kangyan-Zhou 2025-11-08 21:38:48 -08:00
• b142831a26 Fix empty server args in marlin moe test (#12904) Ke Bao 2025-11-09 13:30:47 +08:00
• d134096319 Add Deepseek models into nightly tests (#12865) Kangyan-Zhou 2025-11-08 21:17:49 -08:00
• f290e8016e Revert "Fix spec decoding acc length for dpsk-r1-fp4 tp8" (#12900) Qiaolin Yu 2025-11-08 20:42:42 -08:00
• 9299a62fcb Fix spec decoding acc length for dpsk-r1-fp4 tp8 (#12896) Qiaolin Yu 2025-11-08 19:55:45 -08:00
• 49543be9da Tiny simplify can_run_dp_cuda_graph gather logic (#12891) Liangsheng Yin 2025-11-09 11:15:36 +08:00
• 5236290399 Update CODEOWNERS (#12897) Ke Bao 2025-11-09 09:37:11 +08:00
• b2b26d4324 chore: bump sgl-kernel version to 0.3.16.post6 (#12889) sglang-bot 2025-11-09 09:16:28 +08:00
• d3a03aeef8 Refs/heads/add nightly test multi gpu configs (#12870) alisonshao 2025-11-08 15:14:50 -08:00
• 5f02b918ec [Fix] Fix trtllm-mla backend when chunked prefix cache is disabled (#12361) Baizhou Zhang 2025-11-08 15:10:25 -08:00
• 49653c8896 use fast stream instead of torch.cuda.current_stream in llama 4 shared experts overlap (#12811) b8zhong 2025-11-08 15:04:37 -08:00
• 44f594d832 Apply moe_reduce_sum kernel for fused_marlin_moe (#12888) Ke Bao 2025-11-09 01:31:05 +08:00
• 2b6c4257a0 Fix sending all requests to the first rank in DP attention (#12832) fzyzcjy 2025-11-09 00:18:53 +08:00
• 243ea585fc [DP-Attn] Clarify MLP sync / idle batch preparation logic (#12843) Liangsheng Yin 2025-11-08 23:23:14 +08:00
• 6fee2c535c [CI] Tiny adjust CI esitmation time (#12886) Liangsheng Yin 2025-11-08 23:02:19 +08:00
• f1a9c72de3 Support capturing aux_hidden_states for minimax m2. (#12798) Charles Chen 2025-11-08 01:54:22 -08:00
• 190002c613 [Docs][DeepseekV3.2] Update deepseekv3.2 docs for mha short seq prefill (#12868) YAMY 2025-11-08 00:11:02 -08:00
• 0296f1cdad [Auto Sync] Update activation.py, logits_processor.py, rota... (20251107) (#12853) Lianmin Zheng 2025-11-07 22:07:51 -08:00
• e039ff382c [CI] Fix huggingface access for test_flash_attention_4.py (#12846) Baizhou Zhang 2025-11-07 20:07:06 -08:00
• b8ddc296f4 [sgl-kernel][Deepseek V3.2] Add row_starts to topk kernel (#12582) hlu1 2025-11-07 18:33:27 -08:00
• 0b88d520a0 Add nightly performance test for GPT-OSS 4GPU models (#12805) alisonshao 2025-11-07 16:54:07 -08:00
• d3d7f960b5 [router] Switch MCP tests from DeepWiki to self-hosted Brave search server (#12849) Keyang Ru 2025-11-07 16:16:07 -08:00
• e434187289 [router][grpc] Move all error logs to their call sites (#12859) Chang Su 2025-11-07 15:55:34 -08:00
• fe19a580fb [router][grpc] Refactor: Add builders for chat and responses (#12852) Chang Su 2025-11-07 15:43:32 -08:00
• 55e8e3999c add back flashinfer jit cache to dev docker (#12851) b8zhong 2025-11-07 14:51:24 -08:00
• 32f7982800 sglang diffusion announcement (#12856) Mingyi 2025-11-07 14:35:25 -08:00
• 0f76976c3c remove the fa4 page_size hardcode to 128 restriction on mla model arch (#12801) Rain Jiang 2025-11-07 13:30:30 -08:00
• ae62279071 Fix data parallel controller launch for num nodes > 2 (#12822) Lianmin Zheng 2025-11-07 12:13:21 -08:00
• 5c9273c032 [router] Support structured model output for openai and grpc router (#12431) Keyang Ru 2025-11-07 10:16:45 -08:00
• e316bcacb1 update multimodal_gen readme (#12825) Mick 2025-11-08 01:04:44 +08:00
• 0fe9c1f70b Fix piecewise cuda graph ci test (#12836) Ke Bao 2025-11-08 00:25:00 +08:00
• 61bfd9fa9b optm(checkpoint-engine): disable multi-thread loading when update weights (#12374) Yang Kaiyong 2025-11-07 21:30:04 +08:00
• c67fce160e Fix missing dp_max_padding argument in set_dp_buffer_len (#12812) Chen1022 2025-11-07 21:27:43 +08:00
• bef37d6de8 [Deepseek V3.2] Only skip Indexer logits computation when is_extend_without_speculative (#12816) hlu1 2025-11-07 01:34:04 -08:00
• bc25ea6762 [MoE] Add Comprehensive MoE Integration Tests (#12090) Jonah Bernard 2025-11-07 03:34:46 -05:00
• 1fa788ec14 [Bugfix] Fix illegal memory access (#12758) elvischenv 2025-11-07 13:59:57 +08:00
• 125f76ea44 [Test] Add DeepSeekV3.2 NSA Indexer Test Suite (#12520) Johnsonms 2025-11-06 21:28:43 -08:00
• d8736c756a fix multimodal gen issues (#12765) Yuhao Yang 2025-11-07 13:19:49 +08:00
• 3b1cc466c0 fixes hardcoded "cuda" device references in unit tests to use a dynamic device selection (#12761) Kalyan Kumar 2025-11-07 09:08:35 +05:30
• 0ee5ab5a74 Add PP support for dots_vlm (#12763) Tianyu Guo 2025-11-07 11:14:27 +08:00
• ed5e905c89 [HotFix]: Add missing SGLANG_EPLB_HEATMAP_COLLECTION_INTERVAL env var (#12776) hzh0425 2025-11-07 10:58:44 +08:00
• d9c812d881 [hotfix]: Resolve ModuleNotFoundError in PD deployment for is_in_ci() (#12772) hzh0425 2025-11-07 10:48:03 +08:00
• 7257525cce [DeepSeek-V3.2][NSA] Enable MHA Pathway for Short Sequence Prefill on B200 (SM100) (#12788) YAMY 2025-11-06 17:26:08 -08:00
• 34ba10efd6 [AMD] Update wave-lang to 3.8.2 (#12576) Gaurav Verma 2025-11-06 15:51:44 -08:00
• a119363f08 ignore the deepgemm check when the model weight with nvfp4 and moe ba… (#12782) Rain Jiang 2025-11-06 15:27:28 -08:00
• fb314d7bb1 Add bot-bump-kernel-version-to-sglang workflow (#12794) alisonshao 2025-11-06 14:27:40 -08:00
• 3a64844a1c Fix hang in deepgemm compilation with symmetric memory enabled (#12715) Nicolas Castet 2025-11-06 16:06:22 -06:00
• 585c417fc0 chore: update CODEOWNERS (#12795) Yineng Zhang 2025-11-06 13:11:28 -08:00
• b0d1c21d03 [fix] Only enable flashinfer all reduce fusion by default for single-node servers (#12724) Lee Nau 2025-11-06 11:53:58 -08:00
• b07c5e4080 Pin uvloop to 0.21.0 (#12279) R0CKSTAR 2025-11-07 03:33:31 +08:00
• 1772671be5 [docs] Remove redundant --disable-radix-cache option from (#12717) Rahul Chalamala 2025-11-06 11:25:49 -08:00
• 6e6009fb6b [CPU] Fix TP padding case with weight block size (#8243) jianan-gu 2025-11-07 03:24:48 +08:00
• 88a2a34041 [Fix]HTTP Stream raise exception (#11904) Jimmy 2025-11-07 03:23:12 +08:00
• 78c58621d2 [mem pool] bugfix: wrong position for self.device in Mamba (#12684) Teng Ma 2025-11-07 03:05:42 +08:00
• c3bb348dad [Docs] fix dead links in multiple documentation pages (#12764) Mattheliu 2025-11-07 02:49:32 +08:00
• 4e234b4cf9 [Intel XPU]Update pytorch xpu to 2.9 (#12363) gaopengff 2025-11-07 02:34:23 +08:00
• 4cc725ac1c [Intel]Add 'intel_xpu' attention backend for llama4 (#11051) gaopengff 2025-11-07 02:33:41 +08:00
• 2cb42dc184 [router][grpc] Add more mcp test cases to responses api (#12749) Chang Su 2025-11-06 10:20:00 -08:00
• 0c006b8809 chore: bump SGLang version to 0.5.5 (#12739) sglang-bot 2025-11-07 00:46:19 +08:00
• cd135bfe30 Update dsv3 quantization auto setting for sm100 (#12778) Ke Bao 2025-11-06 22:39:13 +08:00
• fc84b0730c [Refactor] Refactor fused_moe_triton tuning tools: extract shared utils, add EP/MLLM support, reduce overhead (#12440) Xiaoyu Zhang 2025-11-06 20:54:42 +08:00
• 8be0e1bc9c fix ci (#12760) Keyang Ru 2025-11-06 00:21:11 -08:00
• 8e1d6756d5 docs: document video-capable multimodal models (#12565) Amit Prakash 2025-11-06 13:36:19 +05:30
• 0da30dbc20 fix qwen3-omni audio length < 30s (#12674) jiapingW 2025-11-06 16:05:28 +08:00
• 58095cb00a Add timing metrics for requests (#12646) yinghui 2025-11-05 23:07:16 -08:00
• fd3034da75 [VLM] Optimize qwen_vl preprocess_video (#12240) Yuan Luo 2025-11-06 14:55:01 +08:00
• fbbe16faab [GDN] Fuse b.sigmoid(), fused_gdn_gating and unsqueeze into one kernel: up to 0.85% e2e speedup (#12508) Binyao Jiang 2025-11-05 22:52:04 -08:00
• 6a1a64fa41 [BUGFIX] fix output_ids in abort (#12737) Yi Zhang 2025-11-06 14:51:47 +08:00
• e2715cf871 fix mamba prefix cache leak caused by abort (#12693) Yi Zhang 2025-11-06 14:51:03 +08:00
• 74630ba310 [router][ci] Disable cache (#12752) Keyang Ru 2025-11-05 22:49:03 -08:00
• 73e9a2ef5c fix: tiny fix cli (#12744) Mick 2025-11-06 14:45:50 +08:00
• 837b08eb2e [router][grpc] Support mixin tool calls in Responses API (#12736) Chang Su 2025-11-05 21:29:45 -08:00
• bb6a21cd99 [Fix]Tiny fix in Dockerfile (#12748) Baizhou Zhang 2025-11-05 21:04:33 -08:00
• 32ec68faf9 keep attention backend document up to date (#12741) b8zhong 2025-11-05 20:41:20 -08:00
• 3c0a6df82d [chore] Fix triton installation for cu13 image (#12742) Baizhou Zhang 2025-11-05 20:20:18 -08:00
• 2104d20eba Temporarily fix missing routed_scaling_factor for CompressedTensorsWNA16MoEMethod (#12738) Atream 2025-11-06 12:01:03 +08:00
• f235498eca DeepSeek-V3.2: Add Adaptive MHA Attention Pathway for Short-Sequence Prefill (#11892) YAMY 2025-11-05 19:33:26 -08:00
• 149dc9aab1 Add nightly test multi gpu configs (#12721) alisonshao 2025-11-05 19:30:19 -08:00
• 9a954982de [chore] SGLang tag management in Dockerfile (#12734) Baizhou Zhang 2025-11-05 19:03:26 -08:00
• 97be66c358 fix sgl-kernel version (#12723) gongwei-130 2025-11-05 19:01:03 -08:00
• 74243dffa2 Revert "[router] web_search_preview tool basic implementation" (#12716) Keyang Ru 2025-11-05 18:57:39 -08:00