Commit Graph

5061 Commits

Author SHA1 Message Date
ykwd
93088b6975 [Hicache] Mooncake API Fix & Test, and Improved Readme (#9951)
Co-authored-by: Teng Ma <sima.mt@alibaba-inc.com>
2025-09-04 13:55:39 -07:00
Cheng Wan
453511acc7 Save memory for expert model parallel (#9957) 2025-09-04 13:31:47 -07:00
pansicheng
d07304870b fix 3fs zerocopy (#9938)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-09-04 13:24:12 -07:00
Yingchun Lai
b32ab0705e metrics: support customer buckets for prompt/generation_tokens_histogram (#9634) 2025-09-04 22:22:08 +08:00
Huapeng Zhou
75ee00112d [Doc] Fix SGLang tool parser doc (#9886) 2025-09-04 21:52:53 +08:00
Yuan Luo
ec15c8360e Optimize Qwen3-moe model by using flashinfer fused allreduce (#9973)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-09-04 20:48:53 +08:00
hzh0425
106c2b31fb feat(hicache): Add generic hicache ci e2e test and benchmark test (#9846)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-09-04 20:43:46 +08:00
pansicheng
c67569491c Ensure chunked request extension length respects both rem_chunk_tokens and rem_total_tokens limits (#10003) 2025-09-04 04:15:26 -07:00
Liangsheng Yin
27e8ffed37 [1/N] DP-refactor: move dp balance code into scheduler's mixin class (#10004) 2025-09-04 16:53:58 +08:00
wxsm
4dbb34fe43 fix: health_generate endpoint in mini_lb (#9997) 2025-09-04 01:52:28 -07:00
Tony Lu
1e18a341e9 [Bugfix] fix pd chat completion protocol for batching support (#10016)
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
2025-09-04 01:43:16 -07:00
Hubert Lu
2c562fd2d0 Fix Llama 4 with MXFP4 dynamic quant on MI35x (#9993) 2025-09-04 00:48:58 -07:00
kk
b648d86216 [Fix] gpt-oss mxfp4 model run failed on ROCm platform (#9994)
Co-authored-by: wunhuang <wunhuang@amd.com>
2025-09-03 22:34:17 -07:00
Simo Lin
bbf261ae4a [router] fix grpc connection mode detection (#9999) 2025-09-03 21:36:16 -07:00
Simo Lin
4f8a982d52 [router] clean up dependency injector to use ctx (#10000) 2025-09-03 21:35:51 -07:00
Simo Lin
d966b902af [router] move tokenizer, reasoning, tool initialization to server (#9996) 2025-09-03 19:35:13 -07:00
Yineng Zhang
de9217334b feat: add gpt oss b200 ci (#9988) 2025-09-03 17:26:38 -07:00
Lianmin Zheng
397448ebbc [Auto Sync] Update parallel_state.py, few_shot_gsm8k.py (20250903) (#9986)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Leon Gao <leon.gao19@gmail.com>
2025-09-03 16:55:43 -07:00
Elfie Guo
66d5d0425c Minor update regarding issue #9704 (#9733) 2025-09-03 16:52:07 -07:00
Grace Ho
73179b764a nsys profile output kernel classifier (#9314)
Signed-off-by: Grace Ho <grho@nvidia.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
2025-09-03 16:22:33 -07:00
Szymon Ożóg
8cbf71dc2d Triton 3.4.0 MoE config for Deepseek TP16 H100 (#9978) 2025-09-03 13:16:16 -07:00
Xinyuan Tong
56eb5d0a3d fix swa clear(): rename is_in_free_group to is_not_in_free_group (#9914) 2025-09-03 11:42:12 -07:00
timmy-feng
4ed9053ecf Remove mrope position sync (#9460)
Co-authored-by: Nathan Wang <nathan.r.wang@gmail.com>
2025-09-03 11:40:53 -07:00
Tony Lu
5e19b159b0 [router] add chat_template_kwargs in ChatCompletionRequest (#9958)
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
2025-09-03 10:43:52 -07:00
Frank Fang
788b19a532 [router] Add Rerank API Specification (#9906) 2025-09-03 08:30:29 -07:00
Yuhao Yao
f78b7fd16d [1/N][Bug] Fix w4afp8 MoE NaN issue (sgl-kernel) (#9953) 2025-09-03 18:28:27 +08:00
Xiaoyu Zhang
b1fb7e458c [benchmark] add flashinfer_allreduce_fusion benchmark (#9937) 2025-09-03 16:31:01 +08:00
Yineng Zhang
1b2ff4fb7f Revert "Optimized deepseek-v3/r1 model performance on mxfp4 run (#9671)" (#9959) 2025-09-03 00:50:04 -07:00
Yineng Zhang
2c7ca33abb Revert "[Fix] DeepSeek EP accuracy issue on B200 GPUs (#9946)" (#9955) 2025-09-02 23:49:56 -07:00
Ximingwang-09
df397a72e8 [feat] Add P/D attention select for draft model (#9755)
Co-authored-by: 纬杭 <ximing.wxm@antgroup.com>
2025-09-02 22:47:23 -07:00
Liangsheng Yin
5dfcd6c207 add proctitle for tokenizers (#9952)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-09-03 13:31:38 +08:00
kk
0dfd54d11d Optimized deepseek-v3/r1 model performance on mxfp4 run (#9671)
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: wghuang <wghuang@amd.com>
2025-09-02 22:26:28 -07:00
jingyu-ml
bcbeed714f Qwen FP8/NVFP4 ModelOPT Quantization support (#7912)
Co-authored-by: Jingyu Xin <jingyux@nvidia.com>
2025-09-02 20:56:03 -07:00
南京小汤包
cc9a31c662 Update tool_chat_template_deepseekv31.jinja (#9895) 2025-09-02 20:29:21 -07:00
Lianmin Zheng
d631290e32 Remove annoying warnings in sgl kernel build (#9905) 2025-09-02 20:18:25 -07:00
JinYan Su
37565b7f21 fix(cache): move ongoing_prefetch pop after validation to prevent leak (#9927)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-09-03 02:39:34 +00:00
Al-Ekram Elahee Hridoy
6243c36702 [Fix] DeepSeek EP accuracy issue on B200 GPUs (#9946) 2025-09-02 19:31:15 -07:00
Lianmin Zheng
60e37f8028 Move parsers under a single folder (#9912) 2025-09-02 18:25:04 -07:00
Zhiqiang Xie
369b143366 [HiCache] Minor fix on file storage backend (#9869) 2025-09-02 15:52:37 -07:00
tc-mb
03dbf1aa8e [model] support MiniCPM-V 4.0 (#8747)
Signed-off-by: tc-mb <caitianchi@modelbest.cn>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-09-02 15:33:03 -07:00
Chang Su
11dcabc545 Grpc client (#9939) 2025-09-02 11:47:35 -07:00
hzh0425
4d89389c4f Fix the key passing issue in page first layout. (#9929) 2025-09-02 11:30:11 -07:00
Simo Lin
9491d6e554 [router] include rust benchamrks (#9932) 2025-09-02 09:32:09 -07:00
yilian49
f64b8e3e4e Support the internvl3.5 family models in sglang (#9705) 2025-09-02 22:06:48 +08:00
ykwd
53976fce97 [Hicache] Generic page get bugfix (#9909) 2025-09-02 20:22:06 +08:00
Yineng Zhang
18f91eb639 chore: bump v0.5.2rc1 (#9920) 2025-09-02 04:43:34 -07:00
Yineng Zhang
8766b3aca8 fix: update router deps (#9921) 2025-09-02 03:28:58 -07:00
JieXin Liang
1db649ac02 [feat] apply deep_gemm compile_mode to skip launch (#9879) 2025-09-02 03:20:30 -07:00
Xiaoyu Zhang
a1e5d78115 fix parallel_state.py current_platform bug (#9919) 2025-09-02 03:17:15 -07:00
Guoyuan Lin
b7361cc444 [Fix] fix the issue encountered when inference LongCat-Flash/MTP EP MoE on b200 (#9916) 2025-09-02 03:11:14 -07:00