Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• 750ad0d290 [AMD] enable MoRI to release and nightly builds (#18101) HAI 2026-02-02 00:28:30 -08:00
• 86117dfe0e [diffusion] CI: deprecate WarmupRunner in CI (#18038) 陈一涵andMick 2026-02-02 15:16:08 +08:00
• 522e13b4d2 fix: correct weight loading prefix mapping for Qwen3-VL (#18024) 3 people 2026-02-02 13:50:21 +08:00
• a480ca7ead fix: zmq_to_tokenizer encoder transfer when host listens to 0.0.0.0 (#17929) RangerCD 2026-02-02 13:27:27 +08:00
• cd31540fd7 Improve Per Commit Test job filtering for sglang-kernel (#18054) Kangyan-Zhou 2026-02-01 21:15:23 -08:00
• f1824a957b [EPD][refactor]: introduce BaseMMReceiver for gRPC transport integration (#17921) siyu 2026-02-02 11:37:32 +08:00
• ab8b99eb23 Refine logprob logic for request handling (#17986) Cheng Wan 2026-02-01 19:11:52 -08:00
• ea04bc1dd6 [AMD] Fix aiter version in rocm image (#18076) YC Tseng 2026-02-02 11:00:38 +08:00
• 8ed35df204 Add bootstrap_room validation to detect metadata corruption in PD disaggregation (#17430) 3 people 2026-02-02 10:43:50 +08:00
• c84cd4b5ff [diffusion] fix: fix missing component names for VAELoader (#18069) Mick 2026-02-02 09:48:17 +08:00
• 977096ae03 [diffusion] cli: introduce generic attention backend configuration in ServerArgs (#18036) Mick 2026-02-02 09:47:40 +08:00
• d11ccc0a0a fix: avoid double reduce in VLM dp attention (#17991) Yuhao Yang 2026-02-02 09:44:32 +08:00
• 9227d4f748 [Fix] Remove no use code in MiMo-V2-Flash (#18051) Yuan Luoandluoyuan.luo 2026-02-02 07:34:09 +08:00
• 99dad105fd [TestFix] rewrite LoRA overlap loading tests (#18047) Glen Liu 2026-02-01 17:52:08 -05:00
• 993ec178ef [BUGFIX]: using language-only should not reserve space for the vision encoder (#18011) Koushik Duttaandroot 2026-02-01 14:49:00 -08:00
• 1acae30806 [Auto Sync] Update test_deterministic.py (20260131) (#18034) 4 people 2026-02-01 07:40:07 -08:00
• fb609669ca [Auto Sync] Update elementwise.py (20260131) (#18033) Lianmin Zhengandgithub-actions[bot] 2026-02-01 07:39:37 -08:00
• afebb7ab78 Optimize custom-all-reduce (#17674) Yuan Luoandluoyuan.luo 2026-02-01 18:59:31 +08:00
• 4ea4f2a20c [VLM] Optimize get_rope_index for GLM4v (#17420) Yuan Luoandluoyuan.luo 2026-02-01 18:59:15 +08:00
• 0fe282543f [NPU] support the Enable return routed experts (#17025) jiashaokun-1 2026-02-01 18:31:39 +08:00
• 27bec34203 [NPU] disaggregation_decode_enable_fake_auto parameter adaptation (#17811) 3 people 2026-02-01 18:14:26 +08:00
• d9050b4a9c Reset evict swa status when retract (#18059) Ke Bao 2026-02-01 17:17:37 +08:00
• 56907cbcb1 Move deleted 8-GPU tests to test/manual/ (#18060) Alison Shao 2026-02-01 00:21:56 -08:00
• 47592a23c7 [CI] Fix AMD CI by inlining dummy_grok config (#18044) 3 people 2026-02-01 00:20:57 -08:00
• 855dd0546c feat: Add Ling Flash v2.0 support for Eagle3 (#15119) 6 people 2026-02-01 15:57:45 +08:00
• 3ca29dffc7 support qwen3-next eagle3 (#14607) lukec 2026-02-01 15:45:23 +08:00
• 9bb1260558 [Feature] Support file:// URL format for multimodal inputs (#14490) Praneth ParuchuriandYuhao Yang 2026-02-01 13:14:44 +05:30
• 71babdef51 Fix CUDA 12 dependency when importing Mooncake in official CUDA 13.x image (#17540) ZhenshengWuandwuzhensheng01 2026-02-01 15:41:21 +08:00
• 486c7de39f Optimizing all_reduce in RMSNormTP in minimax_m2 (#16483) Roger Young 2026-02-01 15:39:37 +08:00
• 9c168fcac7 Fix Diffusion Request Validation to allow missing input artifacts if the input only contains text (#16610) Kangyan-Zhou 2026-01-31 23:38:40 -08:00
• 4d28cda007 [model] Support MiniCPM-V 4.5 (#9610) tc-mbandXinyuan Tong 2026-02-01 15:37:36 +08:00
• 2c036f1eb1 [Bugfix] fix the display error (inconsistent context) (#17699) linhaifeng 2026-02-01 15:35:11 +08:00
• e5ac6229e1 Fix installation script for H200 runners (#18050) Kangyan-Zhou 2026-01-31 23:30:51 -08:00
• a0bae4c343 Migrate 4-GPU/8-GPU workflow jobs to stage-c and add CI registry decorators (#17299) Alison Shao 2026-01-31 22:37:22 -08:00
• 95180484e9 Disable test_mla_int8_deepseek_v3.py temporarily (#18057) Alison Shao 2026-01-31 22:33:43 -08:00
• d396650bd2 Fix swa kv cache memory allocation (#18039) Ke Bao 2026-02-01 14:26:51 +08:00
• 38d275a9fd [BugFix] fix gpt-oss accuracy issue when enabling piecewise cuda graph (#18013) Minglei Zhu 2026-01-31 22:26:26 -08:00
• 11892599f1 [metric] Optional extra metric labels (#18049) Yinghai Lu 2026-01-31 22:25:59 -08:00
• c7d53fa26a Set torch url index in pyproject.toml (#16802) Baizhou Zhang 2026-02-01 13:23:52 +08:00
• 429ef988bc [BugFix] Fix draft model specified config file (#17815) khalilzhk 2026-02-01 12:45:36 +08:00
• e884b17632 Fix rerun stage command with merged commit history (#17960) Kangyan-Zhou 2026-01-31 20:37:55 -08:00
• 2b2515423a Skipped warning on sm100 (#18000) Kaixi 2026-02-01 05:21:03 +01:00
• d443d2d2ae Improve error output in tnightly tets (#18053) Kangyan-Zhou 2026-01-31 19:26:19 -08:00
• 0f2df9370a feat: validate ib devices in server args (#17598) 3 people 2026-02-01 09:50:42 +08:00
• 398d13a189 [Perf] Add Flashinfer DeepGEMM SM90 for SwapAB Optimization (#15514) b8zhongandBrayden Zhong 2026-01-31 19:56:23 -05:00
• 9951a1ae07 Fix: Remove duplicate assignment for use_w4afp8 (#17858) Chongchong Tian 2026-02-01 08:04:08 +08:00
• c2ab3713e9 [Performance] Optimize Mllama LayerNorm -> Upd (#9725) Yi Zhong 2026-01-31 19:02:57 -05:00
• 6aaea09b3d Update python/sglang/README.md (#18045) Hao Jinandgemini-code-assist[bot] 2026-01-31 13:20:41 -08:00
• 97593c9f41 [CPU] toml file update (#17861) Zaili Wang 2026-02-01 05:16:06 +08:00
• 9ac4dcada4 [Tiny] Fix grammar in shared experts fusion log messages (#18043) Mohammad Miadh Angkad 2026-02-01 05:14:25 +08:00
• 46095f0551 [MUSA] Update 3rd party dir to build/_deps (#18035) R0CKSTAR 2026-02-01 04:02:39 +08:00
• ef134d407d [Fix] Revert back to using CUTLASS mm_fp4 backend (#17369) b8zhong 2026-01-31 10:01:29 -05:00
• 1a006c2a0d [diffusion] refactor: split component_loader into component-wise files (#17820) Mick 2026-01-31 20:22:31 +08:00
• 7412ceb4eb [Auto Sync] Update linear.py to assert shapes (20260130) (#17966) 3 people 2026-01-31 01:01:55 -08:00
• 0e184609d3 Add launch_command assignment in crash dump (#17967) 3 people 2026-01-31 01:00:40 -08:00
• 22498e10c0 [Fix] Triton TP MoE Dpsk V3/Qwen3 Coder with SwapAB (#17965) b8zhong 2026-01-31 02:56:26 -05:00
• a4df95c15f [EPD][Perf] parallelize ZMQ send for encode server (#16487) Zheng Wengangandsiyu 2026-01-31 14:30:11 +08:00
• 04efd03dbf Fix OOM in DeepSeek weight loading by deferring dict(weights) materialization (#17744) jeff 2026-01-31 13:59:00 +08:00
• 45fe51a28e Reduce topk kernel shared memory from 128KB to 32KB for better occupancy (#17747) Yifan CuiandClaude 2026-01-31 13:42:21 +08:00
• c72bf50706 add reasoning_tokens usage test for tool call (#18022) Hudson Xing 2026-01-31 14:09:23 +09:00
• c52578c7fd 【docs】【NPU】Update Expert Parallelism docs for Ascend NPU (#17940) husf 2026-01-31 12:42:11 +08:00
• dc77defdd0 Fix .gitignore may ignore files like core_attention.py (#18021) R0CKSTAR 2026-01-31 12:33:32 +08:00
• d0d9cecd1b Fix cuBLAS >=12.9 detection for cu12/cu13 package naming (#17766) Mohammad Miadh Angkad 2026-01-31 12:01:52 +08:00
• 22aad4e2c4 [Diffusion] Fix FLUX.1-schnell time embedding argument mismatch (#17988) Xiaoyu Zhang 2026-01-31 11:47:27 +08:00
• ec76c390c9 Add ROCm + Mori docker build instructions in rocm.Dockerfile (#18018) kkandwunhuang 2026-01-31 11:12:07 +08:00
• ee3058c6e8 [NPU] fix sgl-kernel-npu package url error in npu.Dockerfile (#18017) 22dimensions 2026-01-31 11:06:58 +08:00
• f6a4ff718f doc update for CANN version (#18014) Tiance Wangandwangtiance 2026-01-31 10:10:23 +08:00
• 5d00150e99 [sglang] fix mm token padded value overlap with text token id (#17781) Bi Xue 2026-01-30 17:09:13 -08:00
• e86476acfc [NPU] support llama-3.2-11B-vision-instruct mode for NPU (#17492) 4 people 2026-01-31 08:49:38 +08:00
• 578b119bc6 [BugFix] Fix server crashes when req.grammar and ngram spec are enabled (#17585) Siyuan Chen 2026-01-31 03:57:42 +08:00
• 81449b4bee Optimize GDN decode for Qwen3 Next (#17094) Sam (Kesen Li) 2026-01-31 01:02:12 +08:00
• abf13ccc11 [Diffusion] Fix lora default lora_scale bug (#17982) Xiaoyu Zhang 2026-01-30 22:04:54 +08:00
• 0c5a81acb8 [BUGFIX] Fix dp size > 1 for qwen3 vl model (#17624) Zheng Liandyizhang2077 2026-01-30 20:44:25 +08:00
• c04efe030a [Model] Add K-EXAONE model support (#16294) 4 people 2026-01-30 21:01:14 +09:00
• 9c2a468e2c update ascend docs (#17987) amote-i 2026-01-30 18:03:55 +08:00
• 8ce9609fa2 fix: fix SHM pointer re-serialization in DP attention (#17930) Fan Yin 2026-01-30 17:03:30 +08:00
• 77a27e728c Add cuda graph status to prefill log (#17836) Ke Bao 2026-01-30 16:56:53 +08:00
• c8dc543dc5 SGLang Tracing: Improve root span attributes (#17008) Haotong Zhang 2026-01-30 16:02:05 +08:00
• a16aba8340 Increase install dependency for gb200 (#17977) Kangyan-Zhou 2026-01-29 23:55:25 -08:00
• 96584ab692 adapt MODELSCOPE download (#17922) jianzhao-xu 2026-01-30 15:26:54 +08:00
• 70db3398d1 [NPU] enhance accuracy for model kimi-vl-a3b-instruct (#17480) McZyWuandcy 2026-01-30 15:19:42 +08:00
• 33c053c50c fix(benchmark): add missing args for speculative decoding benchmark (#17974) cswuyg 2026-01-30 15:05:42 +08:00
• c35aa0238c [CPU][INT4] Add INT4 kernels for CPU (#8226) jianan-guandgemini-code-assist[bot] 2026-01-30 14:30:13 +08:00
• 88f7759402 [CPU] optimize flash_attn_varlen_func (#15708) Ma Mingfei 2026-01-30 14:07:05 +08:00
• 336dc4579e [CPU] Optimize Qwen3-next model on CPU (#12525) 3 people 2026-01-30 14:03:58 +08:00
• 71e4d3b6bc [Intel GPU] fix import error to run DeepSeek-V2-Lite model with BF16 on XPU (#10858) Polisetty V R K Jyothendra Varma 2026-01-30 11:23:53 +05:30
• 7541da15d2 Fix prefill latency performance drop of bench serving (#14592) gaopengff 2026-01-30 13:28:17 +08:00
• 858dc80aff [Intel GPU] fix device in DeepseekScalingRotaryEmbedding to run DeepSeek-V2-Lite BF16 on XPU (#10021) Polisetty V R K Jyothendra VarmaandMa Mingfei 2026-01-30 10:51:38 +05:30
• 0e4d9ddbd6 Fix the scenario where eh_proj is quantized in the bailing moe nextn weights (#17808) LHXuuu 2026-01-30 13:11:47 +08:00
• 606ff09ef8 [Fix] Remove unused Type import in gpt_j.py (#17975) Kangyan-ZhouandClaude Opus 4.5 2026-01-29 21:11:11 -08:00
• 632c7afa8c [Fix] add block size logic for sm120 smem size (#14311) Koushik Dutta 2026-01-29 21:01:57 -08:00
• 046b29be16 GPTJForCausalLM Support (#7839) Wenchen Loandb8zhong 2026-01-29 21:00:04 -08:00
• 22df62d586 add weightless qk norm to RMSNorm interface for Llama 4 (#12813) b8zhongandBrayden Zhong 2026-01-29 22:09:55 -05:00
• 84ab611af8 model: support DeepSeek-OCR-2 (#17897) baonudesifeizhai 2026-01-29 20:49:51 -05:00
• 2cd2c3118d Add concurrency tracking to runner utilization report (#17963) Kangyan-ZhouandClaude Opus 4.5 2026-01-29 17:31:55 -08:00
• b7b1ba329e [AMD] fix pip sglang version (#17950) YC Tseng 2026-01-30 09:19:57 +08:00
• 2b3408ff14 feat: add forward timeout (#17831) StonyPortandqiuxuan.lzw 2026-01-30 08:52:29 +08:00
• 6a6b36367e Fix logprob_start_len handling for prefill-only requests (#17395) Cheng Wan 2026-01-29 15:14:43 -08:00
• c3bf53c7c1 Fix ci weight validation logic to check the safetensor completeness (#17917) Kangyan-Zhou 2026-01-29 13:00:42 -08:00
• 1f75c2af4d Fix /tag-and-rerun-ci to do full rerun when PR has sgl-kernel changes (#17729) Alison Shao 2026-01-29 12:54:30 -08:00