Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• b9eb0d9c2b Change tensor alignment method to mn major (#9844) Mohammad Miadh Angkad 2025-09-02 16:23:13 +08:00
• 1fbfdebe6b [chore] fix dead links in doc (#9913) Lifu Huang 2025-09-02 00:28:26 -07:00
• a25e8e42eb Move multi-tokenizer event loop to better place (#9902) Shangming Cai 2025-09-02 14:12:21 +08:00
• d4a938417d [feat] Support tp mode for DeepSeek-R1-W4AFP8 (#8118) chenxjandyuhyao 2025-09-02 13:17:26 +08:00
• 21e1bc475c [router] fix FunctionCallResponse proto, support arguments is null (#9875) Bruce-x-1997andforestlee95 2025-09-02 11:37:15 +08:00
• 9a0cac1be0 [router] add grpc pd and regular router init (#9893) Chang Su 2025-09-01 20:06:15 -07:00
• b5245064f6 [code style] restruct fused_moe to avoid very long single file (#9878) Xiaoyu Zhang 2025-09-02 11:04:27 +08:00
• 9d9fa9a537 [router] Fix short timeout for the prefill client (#9803) LukasBluebaum 2025-09-02 04:57:04 +02:00
• 58d06fdc95 [HiCacheStorage]: Improve 3fs kvstore‘s performance and resolve mla issues (#9876) hzh0425 2025-09-02 10:01:48 +08:00
• cb9e0e4180 [HiCacheStorage] fix abort request host memory leaks (#9874) huangtingweiandZhiqiang Xie 2025-09-02 09:59:29 +08:00
• 9db8025376 support fp8 kvcache for hybrid attn backend on GPT-OSS (#9783) Rain Jiangandgemini-code-assist[bot] 2025-09-01 12:17:12 -07:00
• 598c0bc19d [router] add tokenizer download support from hf hub (#9882) Chang Su 2025-09-01 10:40:37 -07:00
• b361750a4a Mooncake store get zero copy meta optimization (#9857) huangtingwei 2025-09-01 18:27:56 +08:00
• 16e56ea693 chore: bump v0.5.2rc0 (#9862) Yineng Zhang 2025-09-01 03:07:36 -07:00
• 349b491c63 chore: upgrade flashinfer 0.3.0 (#9864) Yineng Zhang 2025-09-01 03:07:19 -07:00
• 5f77e1292d Support Multi Process Tokenizer Manager(#6555) (#8964) 4 people 2025-09-01 16:00:13 +08:00
• 4750cddf68 Update docker build workflows for gfx942 ROCm 7.0. (#9794) Sai EnduriandHubert Lu 2025-09-01 00:37:12 -07:00
• 065e523d7b Tiny allow DeepGEMM on cu12.9 (#9858) fzyzcjy 2025-09-01 14:29:56 +08:00
• 7de2ce45b2 Disable radix cache in test_lora_update.py for better stability (#9852) Baizhou Zhang 2025-08-31 22:28:22 -07:00
• 8c2ffaaf0f fix(hicahce-long-bench): adjust context workload generator to use full query set (#9847) hzh0425andZhiqiang Xie 2025-09-01 05:51:18 +08:00
• 20445327b2 fix inconsistent arguments for generated shared prefix bench (#9073) Pawel KowalskiandPawel Kowalski 2025-08-31 23:27:33 +02:00
• 6d3c20cf5b fix set_interal_state API (#9850) Liangsheng Yin 2025-09-01 01:31:35 +08:00
• 8b6966d020 [HiCache] Storage Refactoring (#9797) Zhiqiang Xieandpansicheng 2025-08-31 07:58:21 -07:00
• a391f73adc Fuse gate_proj and up_proj in Qwen 2.5 VL's vision MLP (#9661) 5 people 2025-08-31 04:08:28 -07:00
• 25c7395934 Fix input logprob index (#9841) Lianmin ZhengandSheng Shen 2025-08-31 02:56:47 -07:00
• f05c68733e [HiCache] Clear kvcache in storage backend with fastAPI (#9750) Teng Maandhzh0425 2025-08-31 17:41:44 +08:00
• 9a0d0b754d [Performance] Improve Qwen RMSNorm by replacing with native RMSNorm op (#9709) Vincent Zhong 2025-08-31 05:20:50 -04:00
• ba861293cf [feat]Ascend NPU Gemma-3-12b and Gemma-3-27b support (#8909) VDV1985 2025-08-31 10:25:07 +03:00
• c112bcc461 [router] global tool parser registry (#9840) Chang Su 2025-08-30 23:35:39 -07:00
• 5e194b2143 [Model] Support Meituan LongCat-Flash && LongCat-Flash-MTP (#9824) Guoyuan Lin 2025-08-31 14:29:21 +08:00
• fd5ce576a4 Tool parser.benchmark (#9835) Chang Su 2025-08-30 21:08:11 -07:00
• 92d79646e5 [router] add reasoning parser readme (#9837) Simo Lin 2025-08-30 21:06:23 -07:00
• f9076a5a2c hot fix for mooncake batch set api (#9836) Zhiqiang Xie 2025-08-30 21:01:51 -07:00
• 646076b71e Update guidelines for syncing code between repos (#9831) Lianmin Zheng 2025-08-30 16:10:35 -07:00
• 0d04008936 [CI] Code sync tools (#9830) Lianmin Zheng 2025-08-30 16:02:29 -07:00
• 05e4787243 [CI] Fix the trigger condition for PR test workflows (#9761) Lianmin Zheng 2025-08-30 15:47:10 -07:00
• 1e61b4960f [Auto Sync] Update parallel_state.py (20250830) (#9828) 3 people 2025-08-30 14:25:39 -07:00
• 300676afac chore: upgrade transformers 4.56.0 (#9827) Yineng Zhang 2025-08-30 14:07:34 -07:00
• 7fe89f7cdb [sgl-kernel] fix: fix missing FetchContent_Populate for fmt (#9826) PGFLMG 2025-08-31 03:57:42 +08:00
• 9970e3bf32 chore: upgrade sgl-kernel 0.3.7.post1 with deepgemm fix (#9822) Yineng Zhang 2025-08-30 04:02:25 -07:00
• 70eedb58bb Fix typo in warning message about DeepGEMM JIT (#9802) Mohammad Miadh Angkad 2025-08-30 18:35:53 +08:00
• 9c99949ef3 chore: update Dockerfile (#9820) Yineng Zhang 2025-08-30 03:08:14 -07:00
• c5082f0f73 chore: fix cuda driver api issue and bump sgl-kernel 0.3.7.post1 (#9746) Yineng Zhang 2025-08-30 02:01:54 -07:00
• 836873b99f Fix memory leak when aborting decode request in PD-Disagg (#9817) Liangsheng YinandLianmin Zheng 2025-08-30 14:36:03 +08:00
• 8abe8deae6 fix: dsv3 lite q_lora_rank none (#9815) Yineng Zhang 2025-08-29 23:24:14 -07:00
• 1e85589dc5 Make fp4_quantize kernels work on sm103 (#9807) hlu1 2025-08-29 21:15:08 -07:00
• c2a26e725c feature(eplb): add min-rebalancing-utilization-threshold for eplb (#8345) hzh0425andyizhang2077 2025-08-30 11:24:29 +08:00
• 591e6c5983 Small bug fix in transformers model implementation (#9809) yilian49 2025-08-29 19:51:44 -06:00
• 42f34437ab Adds initialize_moe_config to bench_one_batch so MOE backend is respected (#9670) pranavm-nvidia 2025-08-29 17:29:32 -07:00
• 5c34b4f1c7 [NVIDIA] [2/N] Optimize silu_and_mul_scaled_fp4_grouped_quant perf (#9556) Kaixi Hou 2025-08-29 17:17:03 -07:00
• ff9b561817 Fix TRTLLM MLA Cuda KV Blocks Causing accuracy drop (#9675) Faraz 2025-08-29 20:16:10 -04:00
• fcd72bd100 [ModelOpt] Fix Weight Loading for DSR1-FP4 Quantization (#9712) Pavani Majety 2025-08-29 17:13:52 -07:00
• 3d8fc43400 chore: upgrade flashinfer 0.3.0rc1 (#9793) Yineng Zhang 2025-08-29 16:24:17 -07:00
• 87a0f7d2c2 [feat] Support EAGLE3 for Qwen2 (#9216) KerwinKai 2025-08-30 03:59:51 +08:00
• 839c93bd2d feat: add original logprobs to response (#8375) 3 people 2025-08-29 11:43:57 -07:00
• f1e9bbaff5 feat: Add flexible validation for partial weight updates (#9663) 8 people 2025-08-30 02:19:26 +08:00
• 3fd1431df2 support enable in the reasoning field to enable thingking for thinkin… (#9715) gongwei-130 2025-08-29 10:57:32 -07:00
• 161e9dc51e feat(hicache-3fs): 3FS-Store Backup Optimizations For MLA Model. (#9692) hzh0425 2025-08-30 01:48:51 +08:00
• 54e872d343 [HiCache] resolve conflict between chunked-prefill and hicache hit count (#9776) Zhiqiang Xie 2025-08-29 10:30:54 -07:00
• e5b29bf14e [PD] Support get_model_info interface for mini_lb (#9792) Xuchun ShangandTeng Ma 2025-08-29 15:54:03 +08:00
• 9a7c8842ba accomendate json schema in the "schema" field, not in "json_schema" field of response_format (#9786) gongwei-130 2025-08-28 23:51:50 -07:00
• 7a16db9bd9 Make sm100 fp8 kernels available on sm103 (#9789) hlu1 2025-08-28 23:47:29 -07:00
• 09a1df2231 add bench_mix.py (#9788) pansicheng 2025-08-29 14:44:26 +08:00
• 4b7034ddb0 ROCm 7.0 update (#9757) sogalin 2025-08-28 22:24:34 -07:00
• a23c30205d Raise error when topk>1 and page>1 for paged attention backends. (#9784) Liangsheng Yinandgemini-code-assist[bot] 2025-08-29 12:47:34 +08:00
• a7d825fccc Skip some tests on Blackwell (#9777) hlu1 2025-08-28 20:00:32 -07:00
• 38cd5fb1e0 bugfix(hicache): Move exists check before key suffixing (#9749) hzh0425 2025-08-29 09:29:47 +08:00
• 001f51940a [HiCache] change the default policy to write through (#9772) Zhiqiang Xie 2025-08-28 18:28:39 -07:00
• 5ad296bda1 Optimize prefill performance on cpu backend (#8750) Ma Mingfei 2025-08-29 08:21:55 +08:00
• 9f81d741a2 fix: fix MLA for ShardedModelLoader/RemoteModelLoader (#6287) wangyu 2025-08-29 07:10:09 +08:00
• a38c149758 feat(draft_model): support draft_model for RemoteModelLoader (#6407) wangyu 2025-08-29 07:09:52 +08:00
• 74dd4249ac [Feature] Support NPUGraph for DeepSeek on Ascend NPU (#9355) chenxu140andEven Zhou 2025-08-29 07:06:24 +08:00
• dc20c22f76 feat: add tuned fused moe config for GLM-4.5-Air-FP8 tp = 4 on B200 (#9770) zixuanzhang226 2025-08-28 16:00:28 -07:00
• 711390a971 [AMD] Support Hierarchical Caching on AMD GPUs (#8236) Hubert Lu 2025-08-28 15:27:07 -07:00
• 5343058875 [router] grpc router bootstraps (#9759) Simo Lin 2025-08-28 12:07:06 -07:00
• fce7ae33f8 [Sync] Update server_args.py (20250828) (#9745) Lianmin Zhengandgithub-actions[bot] 2025-08-28 10:33:00 -07:00
• 6b39f9cf8c Support compile sgl-kernel on cuda 13.0 (#9721) Rain Jiang 2025-08-28 10:18:03 -07:00
• 07c9d8fba2 [router] add llama3.2 multi json streaming parser (#9735) Simo Lin 2025-08-28 05:57:13 -07:00
• 4a4772ae03 Support speculative decoding in hybrid attention backend (#9573) Qiaolin Yu 2025-08-28 01:11:42 -07:00
• c377923304 [feat] Reduce GPU memory overhead by using weakref (#9673) yhyang201 2025-08-28 16:09:06 +08:00
• f84b57c80e Move git clone command up from README (#9740) Xinyuan Tong 2025-08-28 07:27:00 +00:00
• aee094e430 add support for nvidia/gpt-oss-120b-Eagle3 (#9739) zyksir 2025-08-28 15:20:20 +08:00
• 55349e361d support mooncake store dp attention (#9684) huangtingwei 2025-08-28 12:31:31 +08:00
• e1f7cf57dc [router] additional llama32 parser unit test and multi json support (#9732) Simo Lin 2025-08-27 20:34:11 -07:00
• 2bb9d454b5 [router] additional pythonic parser unit test (#9730) Simo Lin 2025-08-27 19:55:59 -07:00
• d0934a5192 gpt-oss blog reproduction document (#9728) Liangsheng Yin 2025-08-28 10:15:08 +08:00
• 3f2d0cefcd [router] Add MCP Tool Handler (#9615) Keyang Ru 2025-08-27 19:12:39 -07:00
• 8b30bec265 [router] fix error response in pd_router (#9505) Bruce-x-1997andbruce.xu 2025-08-28 10:10:55 +08:00
• 4aeba40d7b [Sync] Update mxfp4.py (20250827) (#9724) 3 people 2025-08-27 17:00:09 -07:00
• 28684f909d [router] upgrade kernel version in pd ci (#9720) Chang Su 2025-08-27 16:02:41 -07:00
• bc80dc4ce0 chore: bump v0.5.1.post3 (#9716) Yineng Zhang 2025-08-27 15:42:42 -07:00
• b962a296ed chore: upgrade sgl-kernel 0.3.7 (#9708) Yineng Zhang 2025-08-27 14:00:31 -07:00
• aa3eba8eb4 [sgl-kernel] misc: update deepgemm version for sgl-kernel (#9340) 3 people 2025-08-28 03:01:30 +08:00
• 07ee0ab750 [router] add gpt-oss and glm4 tool parser (#9703) Simo LinandChang Su 2025-08-27 11:26:00 -07:00
• 5c06dcb75a [router] add kimi-k2 tool parser (#9702) Simo LinandChang Su 2025-08-27 11:04:55 -07:00
• 6f6beca49d [router] add step3 tool parser (#9695) Simo LinandChang Su 2025-08-27 10:44:52 -07:00
• 68a54e063e Sets default model name in request classes (#9683) Xinyuan Tong 2025-08-27 17:43:03 +00:00
• fd18995cf3 Fix get_ip when no external network (#9700) ybyang 2025-08-28 01:28:52 +08:00
• db0831e019 Quick fix for loading processor for supporting internvl3_5 series (#9676) yilian49 2025-08-27 12:05:27 -04:00
• 6e4e1c8cdc [router] add deepseek tool parser (#9694) Simo LinandChang Su 2025-08-27 06:18:24 -07:00