Commit Graph

4808 Commits

Author SHA1 Message Date
Hubert Lu
704ced1b2e [AMD] Remove the deprecated C10_WARP_SIZE (#9356) 2025-08-21 18:16:35 -07:00
Pavani Majety
3cc3d9b950 Add Support for Page Size greater than 1 for Flashinfer MLA Backend (#8593)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
2025-08-21 18:15:06 -07:00
Xinyuan Tong
0b3a5b1151 Update reasoning parser doc (#9468)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-21 17:25:30 -07:00
Xinyuan Tong
6c855db82c Revert "bugfix: Fix output_ids extraction in detokenizer_manager" (#9467) 2025-08-21 17:24:25 -07:00
Yineng Zhang
0f9318f7d0 feat: update auto_choose_speculative_params (#9470) 2025-08-21 17:12:12 -07:00
Yineng Zhang
849957bc76 fix: tmp revert gpt oss tp sharding on hopper (#9469) 2025-08-21 17:03:21 -07:00
Stefan He
cded039b57 [FA3] Init Spec Page Table only when Spec is enabled to save ~40MB (#9455) 2025-08-21 15:11:38 -07:00
zixuanzhang226
275f9df381 feat: add fused moe config for GLM-4.5-Air-FP8 on B200 (#9463) 2025-08-21 15:10:20 -07:00
Xinyuan Tong
e8449ab515 Add deepseek v3.1 thinking parser support and update docs (#9464)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-21 15:09:40 -07:00
Yineng Zhang
4746aaea41 fix: support fb fp8 (#9462) 2025-08-21 14:31:43 -07:00
gongwei-130
10d34f74e2 fix: should return a invalid request response when schema missing (#9461) 2025-08-21 14:06:50 -07:00
gongwei-130
9ba7253094 accomendate reasoning_effort set in chat_template_kwargs (#9458) 2025-08-21 13:22:03 -07:00
Hongbo Xu
9c8e4f69c3 [5/n]decouple quantization implementation from vLLM dependency (#9454) 2025-08-21 12:52:07 -07:00
Simo Lin
78ae175866 [router] add tokenizer benchmark (#9427) 2025-08-21 11:09:39 -07:00
hlu1
dae9a80f43 [fix] Fix mxfp4 weight loading bug with TP sharding in GPT-OSS (#9433)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-21 03:50:51 -07:00
fzyzcjy
e85cb1ce9d Fix quant kernel test errors and benchmark wrong output speeds (#7604) 2025-08-21 03:48:41 -07:00
fzyzcjy
55d336cb08 Refactor weight offloading logic (#8521) 2025-08-21 03:48:13 -07:00
Yuhao Yao
de4990a5b2 [Bug] Fix w4afp8 moe kernel (#9392) 2025-08-21 03:45:18 -07:00
DiweiSun
029e0af31d ci: enhance xeon ci (#9395) 2025-08-21 03:35:17 -07:00
pranavm-nvidia
64574ef8c0 Enables speculative decoding for the trtllm_mla attention backend (#9238) 2025-08-21 01:18:21 -07:00
Kaixi Hou
18da2c96ec [NVIDIA] Fix trtllm fp4 moe backend when used in MTP (#9384) 2025-08-21 00:54:01 -07:00
Liangsheng Yin
9b5f0f64f5 Fix tiny misalign with previous truncation setting in tokenizer_manager (#9430) 2025-08-21 14:05:35 +08:00
Azure
70bb066ee4 Fix FP4 inference corruption issue in glm4.5-air model (#9346) 2025-08-20 22:13:47 -07:00
VDV1985
2c4b4b786b [feature] Ascend NPU graph support (#9399)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: yezhifeng (D) <y00897525@china.huawei.com>
Co-authored-by: anon189Ty <Stari_Falcon@outlook.com>
Co-authored-by: Maksim <makcum888e@mail.ru>
Co-authored-by: ssshinigami <44640852+ssshinigami@users.noreply.github.com>
2025-08-20 21:13:27 -07:00
Martin Vit
7cd2ee06d7 feat: Add Triton fallback option and SM120 MoE configs for FP8 models (#9251) 2025-08-20 19:33:15 -07:00
Liangsheng Yin
eb19ccadae [bug] fix errors related to context length in SD (#9388) 2025-08-21 10:32:34 +08:00
Shangming Cai
25ef53f05f [PD] Fix nvlink transport accuracy through transferring metadata with tcp (#9261)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
2025-08-20 19:29:10 -07:00
Cao E
c674bf9c6b Fix biased_grouped_topk_cpu (#9420) 2025-08-20 19:18:48 -07:00
Qiaolin Yu
af1973b871 Fix max_seq_len_k in trtllm_mha attention backend (#9416) 2025-08-20 19:17:13 -07:00
Chang Su
5cfbb4c136 [router] add glm and step3 reasoning parser (#9415) 2025-08-20 18:33:10 -07:00
Chang Su
e65231022f [router] add tokenizer integration test with real mini tokenizer (#9413) 2025-08-20 17:56:23 -07:00
Keyang Ru
3828db4309 [router] Add IGW (Inference Gateway) Feature Flag (#9371)
Co-authored-by: Yineng Zhang <me@zhyncs.com>
2025-08-20 17:38:57 -07:00
strgrb
88fbc31b50 Support trtllm_allreduce_fusion in flashinfer for cuda<12.8 (#9339)
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
2025-08-20 16:54:30 -07:00
nathan
8f5b9910c1 Add support for Qwen3-seq-cls (#9357) 2025-08-20 16:51:56 -07:00
Mick
ef3004d90a misc: parse bench_serving result as markdown table (#9377) 2025-08-20 16:44:20 -07:00
Xinyuan Tong
84719b527a fix: InternS1 don't recognize image, updates image token for InternVL processor (#9381)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-20 16:43:03 -07:00
jiapingW
e99729c9f3 Fixed the issue where eagle3 TPOT was not as good as without eagle3. (#9404) 2025-08-20 16:42:01 -07:00
Nicolas Castet
c10b8e6a0f Support DP attention with GPT-OSS (#9359) 2025-08-20 16:36:31 -07:00
Lifu Huang
d4bce29721 Fix incorrect logic in chat template handling. (#9336)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-20 16:25:36 -07:00
Lifu Huang
b0980af89f Support pinning adapter via server args. (#9249) 2025-08-20 16:25:01 -07:00
Nathan Wang
24eaebeb4b Fix FlashInfer GPU <-> CPU sync (#9409) 2025-08-20 15:26:12 -07:00
Trevor Morris
a91e90d9a3 [2/2] Fuse routed scaling factor into select_experts (#8690) 2025-08-20 15:10:16 -07:00
Xiaoyu Zhang
f96413c444 Refactor allreduce add rmsnorm pattern (#9278) 2025-08-20 02:03:08 -07:00
Liangsheng Yin
08ebdf79d0 Fix the --allow-auto-truncate argument in tokenizer manager. (#9391)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-20 16:56:47 +08:00
fzyzcjy
42c8704560 Add PDL support for quant kernel and rope kernel (#9106) 2025-08-20 01:56:29 -07:00
Yichen Yan
c9bf3877a0 Reduce overhead for fa by not calling heavy CUDA property check (#7375) 2025-08-20 16:26:28 +08:00
Even Zhou
de2dd73831 Revert "[feature] Rework Ascend NPU graph support" (#9385) 2025-08-20 00:35:10 -07:00
Lianmin Zheng
1ec9769753 [Docs] Update contribution guide (#9383) 2025-08-19 23:37:45 -07:00
Shangming Cai
d8ed60f254 [CI] Fix disaggregation failure tolerance CI (#9378)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
2025-08-19 23:31:08 -07:00
Mingyi
f1b0eda55c [readme] Add SGLang x AMD SF meetup information (#9380) 2025-08-19 22:25:09 -07:00