Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• ba88f1cace Tiny clean router load report logic (#14889) fzyzcjy 2025-12-11 22:50:32 +08:00
• 60560c07a2 [model-gateway] refactor cleanup WorkflowContext.get_or_err (#14890) fzyzcjy 2025-12-11 22:48:30 +08:00
• ca1144212a [diffusion] UX: suppress excessive loggers (#14900) Mick 2025-12-11 22:10:22 +08:00
• 543d62d11a Introduce server_fixtures in sglang.test (#14899) Liangsheng Yin 2025-12-11 22:30:33 +09:00
• 27032cecd9 [Ascend]Support of piecewise graph compilation for prefill on NPU (#12287) Vladimir221andronnie_zheng 2025-12-11 16:10:07 +03:00
• 5d804a3767 [diffusion] feat: support sageattn & sageattn3 backend (#14878) Mick 2025-12-11 20:59:44 +08:00
• 388018a5bd [NPU] adapt dsv3.2 nsa prefill context parallel (#14541) liupeng374 2025-12-11 20:12:59 +08:00
• fca8e88f28 [diffusion] feat: enable torch compile to eliminate GPU bubble (#13641) 5 people 2025-12-11 19:06:32 +08:00
• 45eeeb9a3c Tiny support range ratio in GSP in bench serving (#14828) fzyzcjy 2025-12-11 17:26:07 +08:00
• a368df2818 Tiny add more error info for bench_serving (#14827) fzyzcjy 2025-12-11 17:25:49 +08:00
• f85460fb19 Avoid deleting entire cache for missing shards (#14754 follow-up) (#14853) Alison Shao 2025-12-11 01:17:04 -08:00
• e52cf30e81 fix: adding temporary bypass for nightly tests (#14876) Douglas Yang 2025-12-11 00:09:03 -08:00
• a076d75e98 [Fix] Remove unused import from test_disaggregation_hicache.py (#14880) Shangming Cai 2025-12-11 15:50:47 +08:00
• 8348725d9e [CI][BUG] fix ib setup for disaggregation hicache test (#14877) shicanwei.scw 2025-12-11 15:40:48 +08:00
• 2856624156 Only count limitations for previous runs that reaches the test stages (#14856) Kangyan-Zhou 2025-12-10 23:17:34 -08:00
• b62fe8504c fix nightly vlm ci : restore original eval for requests without regex (#14875) Yuhao Yang 2025-12-11 15:13:25 +08:00
• 624725cb5e Move and update MindSpore docs, make it appear on the online documentation (#14861) 3 people 2025-12-11 15:03:50 +08:00
• 1a96e66493 fix: creating blobs only once for publish trace retries (#14845) Douglas Yang 2025-12-10 22:40:06 -08:00
• 32829b1638 Remove myself to test CI gate issue (#14871) Kangyan-Zhou 2025-12-10 22:37:01 -08:00
• e54307f26a [6/n] Fix num_token_non_padded computation in prefill (#14313) 3 people 2025-12-10 22:15:19 -05:00
• 8642dbe416 Refactor Marlin MoeRunner (#14554) 3 people 2025-12-10 22:15:00 -05:00
• 7dcad45cad [CI] Temp disable gb200 test (#14865) Baizhou Zhang 2025-12-10 19:05:16 -08:00
• 7c985331dd Enable TP for Mamba-based models (#14811) roikoren755 2025-12-11 04:03:50 +02:00
• bd7824b24d Minor code style fix for dllm (#14836) Liangsheng Yin 2025-12-11 10:35:42 +09:00
• 312df1d6c0 Fix TestGLM41VPPAccuracy test flakiness (#14848) Binyao Jiang 2025-12-10 16:59:58 -08:00
• 25e97380e3 Fix CUDA version handling in ci_install_deepep.sh (#14854) Lianmin Zheng 2025-12-10 16:52:30 -08:00
• b6523a4f72 fix: restrict cache validation behaviors to CI only (#14849) Alison Shao 2025-12-10 16:03:53 -08:00
• c51efb8b84 fix fp8 gemm nightly CI (#14844) b8zhongandBrayden Zhong 2025-12-10 15:57:51 -08:00
• bcc5483ed7 [model-gateway] fix import order in oai conversation (#14851) Simo Lin 2025-12-10 15:36:42 -08:00
• ccf2602773 [model-gateway] code clean up on oai router (#14850) Simo Lin 2025-12-10 15:34:27 -08:00
• a4992873d4 Treat unittest SkipTest exception as pass instead of as failure (#14847) Binyao Jiang 2025-12-10 15:28:21 -08:00
• c97ce39181 [AMD] Add model to AMD nightly test (#14442) michael-amd 2025-12-10 11:59:44 -08:00
• c032b559a8 [model-gateway] adds default implementations to RouterTrait in mod.rs (#14841) Simo Lin 2025-12-10 11:46:35 -08:00
• da9b801eb7 fix lora target all + csgmv backend (#14796) b8zhong 2025-12-10 11:42:51 -08:00
• 0e54a69548 [bugfix] qwen25-VL support lora (#14638) Siyuan Chen 2025-12-11 03:38:51 +08:00
• e99ee0c695 [model-gateway] Fix incompatible metric comparison in PowerOfTwo policy (#14823) Praneth Paruchuri 2025-12-11 00:45:38 +05:30
• c1bd5ee8c5 Revert transformers to 4.57.1 (#14801) Yuhao Yang 2025-12-11 03:04:36 +08:00
• ef1ab2302a [Auto Sync] Update tool_chat_template_deepseekv31.jinja (20251210) (#14837) 3 people 2025-12-10 10:56:24 -08:00
• d659873762 [diffusion] CI: use unified sampling_params for CI (#14045) Mick 2025-12-11 01:18:56 +08:00
• 6c5ebc0ef7 [diffusion] parallel: pad tokens for video models under sp (#14833) Mick 2025-12-11 01:15:37 +08:00
• 5b5571a8da Apply back moe_sum_reduce for fused_marlin_moe (#14829) Ke Bao 2025-12-11 00:39:41 +08:00
• 1698c2341b [CI] Reduce stage-b auto-partition from 4 to 2 (#14769) Alison ShaoandLiangsheng Yin 2025-12-10 08:32:33 -08:00
• 3d82c0f17f [model-gateway] support engine response http status statistics in router (#14712) fzyzcjy 2025-12-11 00:30:53 +08:00
• 617e9b3bf8 [model-gateway] support customizing Prometheus duration buckets (#14716) fzyzcjy 2025-12-11 00:30:03 +08:00
• 83e35a7c29 [diffusion] doc: fix tiny typo in multimodal_gen/README.md (#14830) Li Jinliang 2025-12-11 00:27:25 +08:00
• 2543666c8e [model-gateway] add anthropic message api spec (#14834) Simo Lin 2025-12-10 08:26:51 -08:00
• f732f8ea57 Fix CI registry scan to only check test/registered directory (#14812) Alison Shao 2025-12-10 08:09:03 -08:00
• 503880dbbe [CI] fix UT success check in test_eagle_infer_beta_dp_attention.py (#14831) Liangsheng Yin 2025-12-11 01:00:50 +09:00
• b8cfa02c01 [NPU] bug fix for mtp and w4a8 (#14806) liupeng374 2025-12-10 22:55:13 +08:00
• d85fecb536 Tiny fix incorrect worker removal command (#14822) fzyzcjy 2025-12-10 22:29:39 +08:00
• 6634f67bd5 Fix router keep nonzero metrics after worker is deleted (#14819) fzyzcjy 2025-12-10 22:29:30 +08:00
• 5eccaf7737 Support HTTP response status code prometheus metrics (#14710) fzyzcjy 2025-12-10 22:28:57 +08:00
• d7f6320bb8 [model-gateway] Dynamically Populate Tool Call Parser Choices (#14807) Wenyi Xu 2025-12-10 22:04:22 +08:00
• 766476f52a [SMG-GO] implement a Go SGLang Model Gateway - OpenAI Compatible API Server (#14770) ybyang 2025-12-10 22:03:28 +08:00
• 12b7a4fab0 [diffusion] performance: refactor diffusion fuse qkv and apply to qwen-image (#14793) Xiaoyu Zhang 2025-12-10 18:55:41 +08:00
• 02f1e81e2d Revert "fix: checking if tokenizer is in cache before downloading from HF" (#14808) Yuhao Yang 2025-12-10 17:14:35 +08:00
• 908c7186af [diffusion] CI: Add LoRA support to diffusion server configuration and test cases (#14697) Prozac614 2025-12-10 16:51:47 +08:00
• 03836d85d2 [GLM-4.6V] Support Pipeline Parallelism for GLM-4.6V & GLM-4.1V (#14720) Yuan Luoandluoyuan.luo 2025-12-10 16:40:12 +08:00
• 87dbdddc93 [diffusion] profile: early exit when enough steps are captured to reduce the size of the trace file (#14803) Mick 2025-12-10 16:11:22 +08:00
• 56e5c07424 fix b200 fa4 ci (#14788) b8zhong 2025-12-10 00:03:43 -08:00
• 6c9c8da64d fix: add missing logic for SGLANG_USE_MODELSCOPE variable (#14794) yrk111222 2025-12-10 15:49:34 +08:00
• 21028b5507 [RL] support weight reload for low-bit rollout (#9650) 6 people 2025-12-10 15:44:01 +08:00
• b0a25d0913 fix b200 ci (#14786) b8zhong 2025-12-09 23:08:41 -08:00
• 793c98afaf handling incomplete rope_scaling config ci after transformers upgrade (#14784) Yuhao Yang 2025-12-10 14:56:16 +08:00
• b1cbfce612 fix server args bug (#14725) TomerBN-Nvidia 2025-12-10 07:05:05 +02:00
• b0f531ad28 Fix VLM accuracy thresholds for nightly tests (#14777) Alison Shao 2025-12-09 20:59:23 -08:00
• 01835998e1 fix: race condition between validation and download locks (#14761) Alison Shao 2025-12-09 20:36:54 -08:00
• 4285e99da7 [Auto Sync] Update data_parallel_controller.py, detokenizer... (20251209) (#14759) Lianmin Zhengandgithub-actions[bot] 2025-12-09 18:38:38 -08:00
• f077436831 [fix] Fix issues for in-flight weight updates (#14064) ShawnY112358and赵晨阳 2025-12-10 10:12:19 +08:00
• 5e8f544d1b Disable 8-gpu-b200 runner in PR tests (#14768) Alison Shao 2025-12-09 17:47:54 -08:00
• c8d74feb06 fix: adding rate limit warning at verify token permission stage (#14756) Douglas Yang 2025-12-09 17:21:04 -08:00
• cbc7dcdaa7 Re-add the API serving timing metrics. (#14744) Liangsheng Yinandzhanghaotong 2025-12-10 10:17:48 +09:00
• a6dc7d2932 [ci]: Enable the new hf API (#14687) MingxuZh 2025-12-09 17:07:51 -08:00
• 390406c46c [model-gateway] release gateway 0.2.4 (#14763) Simo Lin 2025-12-09 16:34:29 -08:00
• 0c63fb9420 [Feature] Add LoRA support for embedding layers (#14177) 3 people 2025-12-09 15:53:33 -08:00
• 9ad02b799d [Perf] Optimize radix tree for cache-aware load balancin (#14758) Simo Lin 2025-12-09 15:35:29 -08:00
• 18bd8e8d6d Improve CI by trying a warmup before unit tests (#14669) Lianmin Zheng 2025-12-09 15:17:59 -08:00
• 036e64dafa move multi-item scoring functions in tokenizer manager into a separate file (#14740) Lianmin Zheng 2025-12-09 14:47:06 -08:00
• 7c6fb3aa2d fix: making rate limit a warning instead of error (#14753) Douglas Yangandgemini-code-assist[bot] 2025-12-09 13:41:09 -08:00
• 8b0b6a45c8 fix: checking if tokenizer is in cache before downloading from HF (#14698) Douglas Yang 2025-12-09 13:08:07 -08:00
• 55504df2f7 Add FP8 Blockwise GEMM Backend Flag --fp8-gemm-backend (#14379) b8zhong 2025-12-09 12:05:56 -08:00
• 73df7a4e8d [SMG] perf: optimize tokenizer for reduced CPU and memory overhead (#14752) Simo Lin 2025-12-09 11:41:13 -08:00
• 8b98bb768c [model-gateway] optimize core modules (#14751) Simo Lin 2025-12-09 10:54:07 -08:00
• 15bc8cbd74 fix rope parameter initialization error caused by transformers v5.0 update (#14745) Yuhao Yang 2025-12-10 02:51:26 +08:00
• 9496f12d00 [Model] Add PaddleOCR-VL Model Support (#12953) yudian0504andluoyuan.luo 2025-12-10 02:16:02 +08:00
• ab0048793c Revert "[Feat] Add received_time in serving_base" (#14743) Lianmin Zheng 2025-12-09 06:52:27 -08:00
• 6ec77680df [diffusion] feat: support comparing batch perf (#14738) 3 people 2025-12-09 22:48:52 +08:00
• 13680e5542 [Test] Skip STANDALONE speculative decoding tests for different hidden sizes (#14733) Alison Shao 2025-12-09 05:21:35 -08:00
• 98c430e114 fix: prevent HugginqFace access when SGLANG_USE_MODELSCOPE is enabled (#12039) yrk111222 2025-12-09 21:02:05 +08:00
• fe7f91ef82 [Feat] Add received_time in serving_base (#13432) zhanghaotong 2025-12-09 21:00:24 +08:00
• cef5ba65b1 [Bugfix] Fix environ error in scheduler_runtime_checker_mixin.py (#14461) kun-llfl 2025-12-09 20:33:41 +08:00
• 53d170883a Add fuse_marlin_moe test to ci and add new ep test (#14686) Xiaoyu Zhang 2025-12-09 20:17:38 +08:00
• f0e948a0f1 fix the deepep 8 gpu unit test (#14601) Rain Jiang 2025-12-09 01:40:09 -08:00
• 9a426fc5ef [CI] Move mistral large 3 basic to nightly (#14622) Alison Shao 2025-12-09 00:28:44 -08:00
• 66772aa2b4 chore: add code owners for deepseek_v2.py (#14714) Yineng Zhang 2025-12-08 23:24:06 -08:00
• b626334475 fix: make override DeepseekV2Model work (#14707) Yineng Zhang 2025-12-08 23:11:18 -08:00
• 0f8bd55f3e [CI] Fix Llama 3.1 8B FP4 CI (#14699) b8zhong 2025-12-08 22:27:15 -08:00
• da3dc497b0 Fix dp-aware incompatible with completions and chat completions APIs (#14647) fzyzcjy 2025-12-09 13:24:53 +08:00
• 817daba062 Tiny extract select_worker_min_load (#14648) fzyzcjy 2025-12-09 13:22:10 +08:00
• af60cad05d [ci][smg] fix docker release ci and add it to pr test (#14683) Simo Lin 2025-12-08 20:56:38 -08:00