Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• 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 Chen 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 Zheng 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 Zheng 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) Lianmin Zheng 2025-10-24 22:28:01 -07:00
• a04212f128 chore: bump sgl-kernel version to 0.3.16.post4 (#12103) sglang-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) vipwangerxiao 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) Baizhou Zhang 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) Jinwu 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
• 229f236da8 [router] migrate app context to builder pattern 2/n (#12089) Simo Lin 2025-10-24 15:04:32 -07:00
• 5983e5bd1b [router] migrate app context to builder pattern 1/n (#12086) Simo Lin 2025-10-24 13:35:22 -07:00
• 4b046a72d3 docs(server-arguments): add allowed options for each argument (#11560) Jonah Bernard 2025-10-24 14:49:20 -04:00
• 770d63123c [router] fix ut router config init to use build pattern (#12084) Simo Lin 2025-10-24 11:16:31 -07:00
• 14203432b4 fix(compile_utils, ep_moe): update environment variable and dtype check (#12034) ishandhanani 2025-10-24 11:00:12 -07:00
• d7f0d88fa2 [router] implement response api get input item function and refactor input/output store (#11924) Keyang Ru 2025-10-24 10:44:21 -07:00
• fc86b18b3e adjust dynamic vs static outputs comparison in test_lora_update.py (#11884) Glen Liu 2025-10-24 13:35:34 -04:00
• 0bfa394aff [Fix]: HiCache hasher failed when EAGLE mode enabled (#12025) Yuanhang Sun 2025-10-24 23:53:13 +08:00
• e04340bf48 Fix multi processing serializer bug (#11958) fzyzcjy 2025-10-24 22:53:45 +08:00
• 8470133852 [b200] fix piecewise cuda graph launch bug (#12067) Xiaoyu Zhang 2025-10-24 22:36:39 +08:00
• 93ef9a094d [Profiler] expand '~' for torch_profiler_output_dir (#11999) Muqi Li 2025-10-24 17:20:46 +08:00
• b04cd3d487 Add 'gguf' to project dependencies (#12046) Muqi Li 2025-10-24 17:16:19 +08:00
• 7ef5d8afd4 Revise POINTSV15Chat model (#12049) Yuan Luo 2025-10-24 17:09:45 +08:00
• 71d41212e4 Fix dpsk-r1-fp4 launching crash (#12063) Qiaolin Yu 2025-10-24 02:04:50 -07:00
• b9fb74f3bc fix: bench_serving ITL calculation when using spec-decoding (#12064) Xinyuan Tong 2025-10-24 02:02:44 -07:00
• e15b63a182 [Fix] fix missing ipc_name of __getitem__ in some IO structs (#12053) ybyang 2025-10-24 16:59:14 +08:00
• 4060ed37cb Refactoring GLM-4.5 and GLM-4.5V related implementations (#11800) Yuxuan Zhang 2025-10-24 16:22:36 +08:00
• 2342605ef0 Tiny cleanup send_single (#12056) fzyzcjy 2025-10-24 14:53:42 +08:00
• dbf17a8313 [router] Add mTLS Support for Router-to-Worker Communication (#12019) Simo Lin 2025-10-23 23:14:09 -07:00
• 0f0c430e93 Install numactl in Dockerfile for GH200/GB200/GB300 (#11853) fzyzcjy 2025-10-24 12:39:10 +08:00
• 8e797a47f0 fix: the hardcode hf repo name comparison for deepseek-ocr (#12031) Rain Jiang 2025-10-23 21:37:56 -07:00
• aa3003f116 Add gguf dependency for cpu/xpu (#12041) Zaili Wang 2025-10-24 12:13:17 +08:00
• 4793ec7d1a Opt MHA chunked prefix: merge prefix and extend kv cache to run mha once (#10953) Yongfei Xu 2025-10-24 11:58:10 +08:00
• 92009bd28e fix: fix MMMU loading issue (#11759) Zaili Wang 2025-10-24 11:21:38 +08:00
• 4ef981e2b6 Revert "[Fix] Fix lint to pass CI" (#12042) Baizhou Zhang 2025-10-23 19:44:58 -07:00
• 69ed8b67a8 [Fix] Fix lint to pass CI (#12037) Baizhou Zhang 2025-10-23 19:39:38 -07:00
• 1801cd199f support more model in piecewise cuda graph (#11745) narutolhy 2025-10-23 19:31:39 -07:00
• ffc722a690 Revert "lang: support direct video inference" (#12038) Lianmin Zheng 2025-10-23 19:21:31 -07:00
• 49afb3d9d9 Fix(security): block unsafe pickle deserialization to mitigate CVE-2025-10164 (#11909) thelongestusernameofall 2025-10-24 10:12:40 +08:00
• f80371ff8c Use flashinfer_trtllm moe runner backend to gain around 10% perf on b200 fp8 dpsk (#11816) b8zhong 2025-10-23 19:12:15 -07:00
• 62eff37ba1 Refactor Triton-kernel MoE runner integration (#11795) Jonah Bernard 2025-10-23 21:47:28 -04:00
• 47e12e082e Enable Llama 4 + TRTLLM MHA (#12003) b8zhong 2025-10-23 18:22:58 -07:00
• 823b442945 lang: support direct video inference (#9936) Mick 2025-10-24 09:12:39 +08:00
• 14a4d80e57 [8/n] decouple quantization impl from vllm dependency - gguf srt (#11964) Fan Yin 2025-10-24 09:12:00 +08:00
• 1053e1be17 chore: bump SGLang version to 0.5.4 (#12027) sglang-bot 2025-10-24 09:01:40 +08:00
• 9a71500cfb Fixed aarch64 flash-mla (#12009) nvjullin 2025-10-24 08:47:04 +08:00
• 6d6e24bcc4 [router] Add builder pattern for RouterConfig with zero duplication (#12030) Simo Lin 2025-10-23 16:46:10 -07:00
• 2c057fbfa8 Update Github action title for kernel build (#12029) Kangyan-Zhou 2025-10-23 13:39:40 -07:00
• dbd9435dc1 Fix mamba radix cache eviction logic in alloc_req_slots (#11616) Roger Young 2025-10-24 04:07:43 +08:00
• 8ae9d4bb41 Revert "[ROCm] Remove vLLM rope dependency & use AITER impl" (#12028) b8zhong 2025-10-23 12:42:59 -07:00
• 1c304aa9bc Log iteration # for prefill and decode (#9366) Nicolas Castet 2025-10-23 14:28:03 -05:00
• 770529a731 model: support deepseek-ocr (#11891) Mick 2025-10-24 03:15:17 +08:00
• 39c237f02c Add AWQ quantization support for NPU. (#10158) ErvinXie 2025-10-24 03:08:05 +08:00
• 28b8a4064d [router][CI] Clean up imports and prints statements in sgl-router/py_test (#12024) Chang Su 2025-10-23 11:56:57 -07:00
• 8bd26dd4e6 ci: fix night-ci with push retry mechanism (#11765) Mick 2025-10-24 02:31:05 +08:00
• ab07cd3e5a [Auto Sync] Update test_deterministic_utils.py (20251023) (#12022) Lianmin Zheng 2025-10-23 11:20:45 -07:00
• a98496834b Feature/nano v2 offline modelopt fp8 and nvfp4 (#12018) Netanel Haber 2025-10-23 21:16:46 +03:00
• a4b637d87a [router] change ci names and update log level in ci (#12021) Simo Lin 2025-10-23 10:36:19 -07:00
• 96a5e4dd79 [Feature] Support loading weights from ckpt engine worker (#11755) Teng Ma 2025-10-24 00:23:30 +08:00
• b0b4f71679 [Fix] memory leak by overlap + retract (#11981) cctry 2025-10-23 07:59:23 -07:00
• 6c18addb6f Revert "Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4" (#12015) Liangsheng Yin 2025-10-23 21:27:58 +08:00
• 32852fe9e9 Move memory runtime checker to mixin class (#12014) Liangsheng Yin 2025-10-23 20:53:26 +08:00
• 53c2934dce [Router] Consolidate ConnectionMode enum to core module (#11937) Arthur Cheng 2025-10-23 05:15:49 -07:00
• e321c97113 [router] Add comprehensive E2E tests for Response API (#11988) Keyang Ru 2025-10-23 05:13:51 -07:00