Commit Graph

161 Commits

Author SHA1 Message Date
Xinyuan Tong
3e7ff1ab1f fix: reasoning parser when request have enable_thinking flag (#8933)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-07 15:52:06 -07:00
Xinyuan Tong
3fa3c6cd6a Enables force reasoning based on chat template for Qwen3-Thinking (#8369)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Chang Su <csu272@usc.edu>
2025-08-06 20:02:47 -07:00
Lifu Huang
6210e2c4f0 Support GPU pinning for LoRA (#8697) 2025-08-06 19:39:45 -07:00
Chang Su
92cc32d9fc Support v1/responses and use harmony in serving_chat (#8837)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-06 16:20:34 -07:00
Yineng Zhang
3ae8e3ea8f chore: upgrade torch 2.8.0 (#8836) 2025-08-05 17:32:01 -07:00
Yineng Zhang
4f4e0e4162 chore: upgrade flashinfer 0.2.10 (#8827) 2025-08-05 12:04:01 -07:00
Yineng Zhang
1ea94d3b92 chore: upgrade flashinfer v0.2.9 (#8780) 2025-08-04 21:59:18 -07:00
ybyang
6f9baf1002 [Improvements] Merge health check route (#8444)
Signed-off-by: ybyang <ybyang7@iflytek.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Kan Wu <wukanustc@gmail.com>
2025-08-03 01:59:06 -07:00
Guanhua Wang
f7b2853ff8 [feat] support minimum token load balance in dp attention (#7379) 2025-08-03 00:46:47 -07:00
Nicolas Castet
82e6c3a65a Add support for NCCL symmetric memory for TP allreduces (#8238) 2025-08-01 23:30:55 +00:00
Cheng Wan
7a1f7fc504 [Feature] Hybrid EP and TP (#8590) 2025-07-31 02:53:25 -07:00
Cheng Wan
e179e0b797 update sgl-kernel for EP: python part (#8550) 2025-07-31 00:14:39 -07:00
Chang Su
a79a5d7012 Revert "Fix the input tools format and history tool_calls in OpenAI API (#6556)" (#8584) 2025-07-30 13:12:05 -07:00
Lianmin Zheng
a4c3b121d8 Split the scheduler into multiple mixin classes to reduce the file size (#8483) 2025-07-29 12:46:50 -07:00
Timofey
c8f549d96d Fix parsing ChatCompletionMessage (#7273)
Co-authored-by: Timofey K <timosha1113@gmail.com>
2025-07-28 11:35:14 -07:00
harrisonlimh
747dd45077 feat: throttle requests at scheduler based on --max_queued_requests (#7565) 2025-07-28 22:32:33 +08:00
Chang Su
b47eda3316 bugfix: Fix multiple finish_reason chunks and tool_calls finish reason check (#8417) 2025-07-27 13:31:06 -07:00
Binyao Jiang
e983d66680 Fix: Improve test_openai_function_calling unit test and fix reasoning_parser.py think_start_token logic (#8316)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2025-07-27 13:12:59 -07:00
Yineng Zhang
10ee89559e chore: upgrade flashinfer v0.2.9rc2 (#8406) 2025-07-27 01:41:22 -07:00
Yingchun Lai
36d6f0ba5b fix: fix the missing metrics on non-rank0 nodes (#7720) 2025-07-27 00:55:25 -07:00
Lianmin Zheng
ed2e313eb6 Clean up server_args, triton cache manager (#8332) 2025-07-25 14:14:51 -07:00
Ying Wang
7ad6b766c5 fix: Fix failed functional tests https://github.com/meta-llama/llama-stack-evals (#8266) 2025-07-24 23:11:32 -07:00
Swipe4057
8d1c5b948e chore: upgrade flashinfer v0.2.9rc1 (#8301)
Co-authored-by: Yineng Zhang <me@zhyncs.com>
2025-07-24 14:29:56 -07:00
Simo Lin
5dd0f870ab [bug] fix pd completion protocol for batching support (#8317) 2025-07-23 23:18:17 -07:00
Yineng Zhang
4953f4ca9a chore: upgrade sgl-kernel 0.2.7 (#8304) 2025-07-23 15:07:27 -07:00
xianzhiT
c87d4fec99 Fix the issue of incorrect finish reason in final stream response chunk returned during tool call (#7708)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-07-23 13:28:53 -07:00
Yineng Zhang
74f59ae555 chore: upgrade sgl-kernel 0.2.6.post1 (#8202) 2025-07-21 02:10:24 -07:00
Lianmin Zheng
55381a46ac Revert "[Feature] Simple Improve Health Check Mechanism for Production-Grade Stability" (#8181) 2025-07-19 22:41:30 -07:00
ybyang
4540a4666a [Feature] Simple Improve Health Check Mechanism for Production-Grade Stability (#8115)
Signed-off-by: ybyang <ybyang7@iflytek.com>
2025-07-19 18:10:00 -07:00
Yineng Zhang
561dd7b2ce chore: upgrade sgl-kernel 0.2.6 (#8166) 2025-07-19 03:17:08 -07:00
jiawei
f1f1d1d40d Fix the input tools format and history tool_calls in OpenAI API (#6556) 2025-07-15 00:58:55 -07:00
Xinyuan Tong
6e923dbd30 feat: update multimodal data handling in engine entrypoint (#8002)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-07-15 00:12:22 -07:00
Yineng Zhang
732fc8e405 chore: upgrade sgl-kernel 0.2.5 (#7971) 2025-07-11 20:35:06 -07:00
Mick
b5e3d6031c vlm: support video as an input modality (#5888) 2025-07-09 23:48:35 -07:00
kyleliang-nv
dd445a41f5 [feature] Add start step profile argument in /start_profile (#7608) 2025-07-09 18:42:15 -07:00
Brayden Zhong
a37e1247c1 [Multimodal][Perf] Use pybase64 instead of base64 (#7724) 2025-07-08 14:00:58 -07:00
Yineng Zhang
62f5522ffe chore: upgrade sgl-kernel v0.2.4 (#7801) 2025-07-05 17:37:40 -07:00
Yineng Zhang
77cfea689d chore: upgrade sgl-kernel v0.2.3 (#7786) 2025-07-05 01:55:55 -07:00
Zilin Zhu
af46f299f9 [RL] add pause and continue generation for async rl training (#7419) 2025-07-04 18:49:49 -07:00
Yi Zhang
489934be0a fuse renormal into moe topk softmax kernel python code (#7751)
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: zhyncs <me@zhyncs.com>
2025-07-03 16:22:14 -07:00
Albert
d3c275b117 Support updating weights at once by stopping all requests (#6698)
Signed-off-by: Tianyu Zhou <albert.zty@antgroup.com>
Co-authored-by: Zilin Zhu <zhuzilinallen@gmail.com>
2025-07-02 22:26:06 -07:00
Zilin Zhu
0626f678de [RL] support update_weights_from_distributed with different group and multiple weights (#7292) 2025-07-02 19:29:11 -07:00
Zilin Zhu
09e699bba4 [RL] add --skip-warmup (#7416) 2025-07-02 18:50:43 -07:00
Yineng Zhang
f18a8fddd4 chore: upgrade flashinfer v0.2.7.post1 (#7698) 2025-07-01 14:05:57 -07:00
Zhiqiang Xie
f9eb04ddb2 upgrade sgl kernel to 0.2.1 for main (#7676) 2025-07-01 00:00:13 -07:00
Yineng Zhang
392e441ad1 chore: upgrade flashinfer v0.2.7 jit (#7663) 2025-06-30 13:26:26 -07:00
Lianmin Zheng
22352d47a9 Improve streaming, log_level, memory report, weight loading, and benchmark script (#7632)
Co-authored-by: Kan Wu <wukanustc@gmail.com>
2025-06-29 23:16:19 -07:00
Lianmin Zheng
071a1f51ae [Minor] clean up multimodal processor and tokenizer manager (#7624) 2025-06-29 02:50:14 -07:00
Lifu Huang
49538d111b Support dynamic LoRA loading / unloading in engine/server API (#7446) 2025-06-27 21:00:27 -07:00
mlmz
fe2a0f962f minor: 'role' must be system/assistant/tool, but case insensitive for now (#7499) 2025-06-25 02:11:03 -07:00