Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• fafaa2ccea [BugFix] fix outplace_fused_experts missing is_gated (#13864) Minglei Zhu 2025-11-24 12:36:14 -08:00
• 9b4b344115 [model-gateway] add grpc server code owner (#13865) Simo Lin 2025-11-24 12:29:57 -08:00
• 94216a9cc4 Fix quantized moe checker fail for Qwen3 dense fp8 model (#13853) fzyzcjy 2025-11-25 03:16:50 +08:00
• 9535015d05 [Perf] Optimize DeepSeek-R1 w4afp8 glue kernels (#10027) Yuhao Yao 2025-11-25 03:05:38 +08:00
• a3b578fc60 [model-gateway] Refactor router e2e responses tests (#13745) Xinyue Zhang 2025-11-24 10:58:53 -08:00
• b60e769d0e Tiny unpin uvloop for other backends (#13858) Liangsheng Yin 2025-11-25 01:34:57 +08:00
• a95a38078b [Fix] Fix uvloop get_event_loop() is not suitable for 0.22.x (#13612) Zhi Yiliu 2025-11-25 01:20:00 +08:00
• 98b38de3f2 Fix: Safe RoPE Cache Expansion to Prevent Position-ID Out-of-Bounds in EAGLE + Long-Sequence Workloads (#11871) YAMY 2025-11-24 09:19:06 -08:00
• a146f833f1 [Fix]: Adjust FutureMap's token_id_bufs Size to Prevent ChunkedPrefill's next_token_ids from Overwriting Previous Prefill Requests' next_token_id (#13713) ant-yy 2025-11-25 01:08:52 +08:00
• 1dd9a6ae4d Fix TorchAO quant in VLM (#13508) StonyPort 2025-11-24 22:15:40 +08:00
• 8ef11569a2 [VLM] Revise InternVL Piecewise CUDA Graph Supporting (#13846) Yuan Luo 2025-11-24 22:15:10 +08:00
• ecefc7904f [sgl-kernel Code Clean] Remove useless lightning_attention kernel (#13819) Xiaoyu Zhang 2025-11-24 18:26:25 +08:00
• aeac622058 [Intel XPU]support xgrammar backend for intel xpu (#13245) gaopengff 2025-11-24 16:48:00 +08:00
• 04b52fa8d6 [chore]Upgrade flashinfer to 0.5.3 (#13751) Baizhou Zhang 2025-11-23 23:38:36 -08:00
• e5c0f59133 [diffusion] CI: send nightly-test outputs of diffusion to slack for correctness monitoring (#13833) Yuhao Yang 2025-11-24 15:22:26 +08:00
• 981ca8313f [misc] Rename minilb install env & remove files & fix lint (#13831) Liangsheng Yin 2025-11-24 13:50:00 +08:00
• 414248e0d0 [diffusion] doc: minor update contributing.md with test section (#13792) Mick 2025-11-24 13:00:08 +08:00
• f56b9b42e6 [Bugfix] Add jit kernel files in packaging (#13829) Yuan Luo 2025-11-24 12:32:16 +08:00
• b2f7b08c49 Refactor cache init logic (#13800) Liangsheng Yin 2025-11-24 11:41:46 +08:00
• 75222bfed9 Update MindSpore documentation (#13656) Tiance Wang 2025-11-24 11:20:51 +08:00
• 9ea1953331 [Doc] Refine fused_moe_triton configs doc (#13820) Xiaoyu Zhang 2025-11-24 11:09:41 +08:00
• dbf22152d6 Fix bug: Incorrect variable used in rem_total_token_offset calculatio… (#13201) liuhuijiayou 2025-11-24 11:04:34 +08:00
• d5e0346847 xgrammar up version to 0.1.27 (#13650) Swipe4057 2025-11-24 05:53:45 +03:00
• a22104a676 chore: bump sgl-kernel version to 0.3.18 (#13816) sglang-bot 2025-11-23 17:24:54 -08:00
• 4683e244fe [1/2] Refactor DeepGeem requant for FP8 Linear on Blackwell (#13601) Baizhou Zhang 2025-11-23 16:07:56 -08:00
• 9054e844ea remove package json which is not used (#13810) Simo Lin 2025-11-23 15:00:30 -08:00
• 18403f6bfe make trtllm attn backend's init_forward_metadat non blocking (#13802) yinghui 2025-11-23 22:35:40 +01:00
• 2892265d4c Tune fp8_w8a8 fused triton moe for GLM-4.6-FP8 (#13815) Qiaolin Yu 2025-11-23 13:29:54 -08:00
• c9bd1aca32 [CI] Tiny refactoring sgl-kernel tests (#13813) Baizhou Zhang 2025-11-23 12:45:17 -08:00
• 618ca23802 [Deepseek] Refactor deepseek server_args _handle_model_specific_adjustments (#13687) hlu1 2025-11-23 12:41:14 -08:00
• 5c2915494c [Scheduler] Tiny organize code style (#13806) Liangsheng Yin 2025-11-23 23:41:34 +08:00
• aaa40a9b3b Fix pagination bug in CI monitor preventing performance-test-2-gpu data collection (#13781) alisonshao 2025-11-23 06:02:30 -08:00
• dd70cf99c1 [diffusion] CI: add run_suite to multimodal_gen CI (#13791) Mick 2025-11-23 21:27:33 +08:00
• d4593964fe [diffusion] feat: support sp for image models (#13180) Mick 2025-11-23 18:11:42 +08:00
• 53fffefd5d Upgrade flashmla kernel for NSA tp support (#13718) YAMY 2025-11-23 01:36:49 -08:00
• b964ce61d6 [DeepEP] Add SGLANG_DEEPEP_BF16_DISPATCH env var in Normal mode (#13787) Xiaoyu Zhang 2025-11-23 17:32:43 +08:00
• ac5505b04c [Feature] HiCache JIT kernel (once again) (#13764) DarkSharpness 2025-11-23 14:19:16 +08:00
• a90435c059 Fix typo in docs (#13709) Peiqi Yin 2025-11-23 10:49:49 +08:00
• 5354d7b7fd [model-gateway] clean up router manager function order (#13776) Simo Lin 2025-11-22 16:16:20 -08:00
• e01486778a [model-gateway] update smg code owner (#13777) Simo Lin 2025-11-22 15:50:53 -08:00
• 047935080d Revert "Fix RMSNorm API CALL mismatch issue. (#10032)" (#13727) ErsongWang 2025-11-23 06:25:52 +08:00
• cad7878964 Gather static input buffers for cuda graph (#13676) cctry 2025-11-22 13:01:50 -08:00
• b29769f3b6 Move unnecessary input_addr capture under debug mode flag for speed-up (#13690) Binyao Jiang 2025-11-22 11:42:26 -08:00
• 3990b84bd3 Refactor MHA & MLA KV caches to support FP4 (#13547) Ho-Ren (Jack) Chuang 2025-11-22 11:13:43 -08:00
• 5a4394a342 align code style eagle draft&draft_extend cuda graph runner (#13533) yinghui 2025-11-22 18:55:16 +01:00
• dd303614e0 [diffusion] CI: tinyfix diffusion ci (#13769) Yuhao Yang 2025-11-23 01:03:36 +08:00
• 863124684c [Spec v2] Remove allocate_lens and enable over-allocation (#13478) Liangsheng Yin 2025-11-22 22:49:10 +08:00
• 5625e32cae [VLM] Replace torch.repeat_interleave with faster np.repeat for Qwen-VL series (#13736) Yuan Luo 2025-11-22 22:45:32 +08:00
• ca548d8324 [diffusion] refactor: refactor sampling params (#13706) Mick 2025-11-22 22:43:04 +08:00
• 3397bcee84 Tiny support different prompts in send_one.py (#13768) Liangsheng Yin 2025-11-22 21:59:58 +08:00
• 3e804bb0ba Update mem checker during busy (#13704) Liangsheng Yin 2025-11-22 21:15:02 +08:00
• a22de641ef [diffusion] fix: fix hunyuanvideo and add 2-gpu ci test (#13720) Yuhao Yang 2025-11-22 20:54:51 +08:00
• ac43822634 Refactor eagle bigram key matching (#13714) Liangsheng Yin 2025-11-22 20:40:42 +08:00
• a92afb00c6 [Ascend] support Kimi-K2-Thinking (#12759) Yijie Zhu 2025-11-22 17:33:07 +08:00
• 0eea17e3b5 Use dual stream for DS MoE whenever cuda graph is used (instead of with token threshold) (#9405) Trevor Morris 2025-11-22 08:37:41 +00:00
• 3805243245 modularize gsm8k and mmmu test classes (#13506) Netanel Haber 2025-11-22 10:06:53 +02:00
• 8bfce9b08d [Tiny] Renaming environ for NVFP4 dispatch (#13756) Baizhou Zhang 2025-11-22 00:05:20 -08:00
• b41afa3754 [Auto Sync] Update evict_policy.py, radix_cache.py (20251120) (#13669) Lianmin Zheng 2025-11-21 22:07:36 -08:00
• 94ae816f29 Fix model weights validation with automatic cache cleanup (#13729) alisonshao 2025-11-21 19:40:00 -08:00
• 53620a1b1a fix test_lora_update.py starvation message check (#13702) Glen Liu 2025-11-21 22:33:04 -05:00
• 59b4d7f8d6 Fix B200 Nightly tests and move one manual test back to unit test to prevent the same issue (#13746) Kangyan-Zhou 2025-11-21 17:41:12 -08:00
• a56f770277 Fix global scaling factor loading hang (#13484) Shu Wang 2025-11-21 18:07:06 -06:00
• 1b48e1b974 Feat/nemotron nano v3 support (#12690) roikoren755 2025-11-21 23:53:05 +02:00
• a24aefe562 add some more labels (#13701) b8zhong 2025-11-21 11:29:33 -08:00
• 45c572c58f Support torch 12.9 + DeepEP by removing custom nvshmem (#12949) fzyzcjy 2025-11-22 03:11:43 +08:00
• 681b9e6425 Revert "enable csgmv automatically on cuda" (#13707) Qiaolin Yu 2025-11-21 10:37:41 -08:00
• dab06b50ab Fix: CI monitor should not exit with error on regressions (#13694) alisonshao 2025-11-21 10:01:48 -08:00
• 85ffce30af [Piecewise CUDA Graph] Support Kimi-K2 (non-Thinking) (#13466) b8zhong 2025-11-21 09:39:59 -08:00
• e94ef9fcae Add to ci permission (#13739) Jiajun Li 2025-11-21 12:21:09 -05:00
• 964cdedc50 [CI] minor hot fix of model validation list (#13737) Liangsheng Yin 2025-11-22 01:00:41 +08:00
• aa6e2c8aa0 [diffusion] log: minor improve logging (#13735) Mick 2025-11-21 23:01:23 +08:00
• 1776dce557 Super tiny delete unused files (#13734) fzyzcjy 2025-11-21 22:26:39 +08:00
• 99e13d189b Fix url: use https://roadmap.sglang.io for roadmap (#13733) Lianmin Zheng 2025-11-21 05:42:32 -08:00
• dc836909a6 fix 3fs down, lock schedule main thread (#13407) weibingo 2025-11-21 19:02:36 +08:00
• 323fed5cfd [diffusion] doc: add contributing.md (#13649) Mick 2025-11-21 19:00:27 +08:00
• eff7df6d0a [AMD] Enable fused shared expert append and flatten quant for fp8 deepseekR1 model (#13705) jacky.cheng 2025-11-21 18:48:28 +08:00
• 5e7f91d451 [diffusion] profile: support performance metric dumping and comparison (#13630) Mick 2025-11-21 18:47:16 +08:00
• a34d3abb54 [Clean code] Compressed_tensors_moe code clean (#13719) Xiaoyu Zhang 2025-11-21 18:15:46 +08:00
• 6d0e0b9bfc [11/N] MoE Refactor: Simplifying SBO Implementation with Dispatcher Hooks (#13327) Cheng Wan 2025-11-21 01:11:37 -08:00
• 589d9ad55b [NPU] chore: bump to CANN 8.3.RC1 and Pytorch 2.8.0 (#13647) Even Zhou 2025-11-21 17:07:08 +08:00
• a244c0309c [Fix] Qwen3Next lmhead dtype (#13708) Ziming Huang 2025-11-21 16:01:33 +08:00
• 1bb063aac8 [HiCache] fix unit test with changed new APIs (#13498) Teng Ma 2025-11-21 15:40:31 +08:00
• b30f63c40f [Bugfix] Fix hidden state size in EAGLE PD disaggregation buffers (#13590) Michele Marzollo 2025-11-21 08:32:40 +01:00
• 90a0133515 [Auto Sync] Update http_server.py, io_struct.py, scheduler_... (20251120) (#13679) Lianmin Zheng 2025-11-20 23:17:15 -08:00
• 4360279036 [diffusion] server: use meta to avoid Linear init for TextEncoder (#13564) zyksir 2025-11-20 23:14:24 -08:00
• b537ac0d1f Fix ZMQ bind error on non-zero rank nodes when using SGLANG_BLOCK_NONZERO_RANK_CHILDREN=0 (#13686) ishandhanani 2025-11-20 22:54:41 -08:00
• eda2f70033 [diffusion] doc: minor update docs (#13177) Mick 2025-11-21 14:35:29 +08:00
• 8c212a2029 [difusion] CI: speed up multimodal_gen ci (#13665) Yuhao Yang 2025-11-21 14:26:33 +08:00
• d754ce973e [Piecewise Cuda Graph] rename, refactor and add more logging (#13675) Stefan He 2025-11-20 21:28:38 -08:00
• 475962a139 [VLM] Support Piecewise CUDA Graph for InternVL (#13640) Yuan Luo 2025-11-21 13:21:51 +08:00
• bfcf15a129 [opt kimi k2 4 / n] Delete useless pad kernel in sgl_moe_align_block_size (#13587) Xiaoyu Zhang 2025-11-21 13:16:42 +08:00
• fb04d43428 [kimi k2 thinking] Avoid useless torch.zeros_ (#13596) Xiaoyu Zhang 2025-11-21 13:15:27 +08:00
• 6be65ae462 Fix target MLA with eagle3 support for PD disaggregation (#13555) Mike Qiu 2025-11-21 12:16:05 +08:00
• 750084ae08 remove unnecessary starvation check (#13619) Glen Liu 2025-11-20 22:10:51 -05:00
• 64480ec712 Add sgl-kernel CI test for Blackwell (B200) (#13301) alisonshao 2025-11-20 19:02:42 -08:00
• db2d362d04 [NVIDIA] Add cutedsl e2e test to GB200 CI (#12672) Kaixi Hou 2025-11-20 18:30:12 -08:00
• 81e86992cd [CI] Move nightly tests to test/nightly/ (#13683) alisonshao 2025-11-20 18:00:02 -08:00
• c4db77f8a9 [model-gateway] fix gateway cli arg parser to not use = (#13685) Chang Su 2025-11-20 17:57:17 -08:00
• c0a2513b07 [diffusion] CI: improve validation method (#13627) Mick 2025-11-21 09:13:13 +08:00
• 3ae664d786 [model-gateway] add both python and rust cli alias (#13678) Simo Lin 2025-11-20 17:00:28 -08:00