Commit Graph

4853 Commits

Author SHA1 Message Date
Yineng Zhang
c807cd7c75 chore: update configurer (#9557) 2025-08-24 01:05:00 -07:00
Vincent Zhong
327f7b7c87 fix(grok): remove duplicate replicate_lm_head configuration (#9549) 2025-08-23 19:49:24 -07:00
Xiaotong Jiang
80425e59bb [doc] deepseekv31 support (#9544) 2025-08-23 16:54:58 -07:00
Mingyi
af9d4eb038 [readme] Include additional resources for the SGLang x AMD SF Meetup event (#9547) 2025-08-23 16:51:16 -07:00
gongwei-130
fb107cfd75 feat: allow use local branch to build image (#9546) 2025-08-23 16:38:30 -07:00
Lianmin Zheng
97a38ee85b Release 0.5.1 (#9533) 2025-08-23 07:09:26 -07:00
Lianmin Zheng
86d10d220f Update grok.py and tiktoken tokenizer (#9532) 2025-08-23 05:40:18 -07:00
hzh0425
83871aa12d feat(hicache): Supports 3fs-hicache compatibility with dp-attention (#9372) 2025-08-23 02:08:32 -07:00
fzyzcjy
b1b3f0b38f Partially unify triton per token group quant kernels (#9485) 2025-08-23 02:07:31 -07:00
fzyzcjy
34e5e11f0f Tiny make device_loading_context more static (#9478) 2025-08-23 02:07:15 -07:00
fzyzcjy
2600fc0d47 Overlapped weight offload (#8034) 2025-08-23 02:06:46 -07:00
hlu1
ccd3fb946e [fix] Fix mxfp4 triton MoE tp bug (#9473)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
2025-08-23 01:48:40 -07:00
Chang Su
c9dd70fbde tool-call(dsv3): Improve deepseek-v3 chat template and tool_choice = required (#9525) 2025-08-23 01:46:56 -07:00
Yineng Zhang
6b2b8bf0e1 fix: blackwell dsv3 fp8 issue temporary solution (#9530) 2025-08-23 01:33:21 -07:00
yuxingcyx
4edbe0d534 [benchmark] Add benchmark scripts for ceval and boolq (#8946)
Co-authored-by: chenyuxing <2818499974@qq.com>
Co-authored-by: hanqing <huang010706@126.com>
Co-authored-by: Muggle <62579327+trawolf@users.noreply.github.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
2025-08-23 15:40:15 +08:00
fzyzcjy
0374304a2c Add enable_flashinfer_mxfp4_bf16_moe for higher precision and slower moe backend (#9004) 2025-08-23 15:38:40 +08:00
Chanh Nguyen
127d4b0d5e Support GC Freezing to improve latency & throughput (#9241)
Co-authored-by: Chanh Nguyen <cnguyen@linkedin.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
2025-08-23 13:43:09 +08:00
Moein Khazraee
7e880286b5 Add support for extensions of interface and pre-registrations to NIXL HiCache (#9211)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-08-22 20:06:13 -07:00
Bruce-x-1997
446c8e4cdb [router] ignore client error when record failure in pd_router (#9503)
Co-authored-by: bruce.xu <bruce.xu@gmicloud.ai>
2025-08-22 14:19:45 -07:00
Keyang Ru
5ef545e678 [router] Move all protocols to spec.rs file (#9519) 2025-08-22 14:18:47 -07:00
sogalin
c4500233ff Add Qwen3-30B-A3B-Thinking-2507 support on AMD GPUs. (#9456) 2025-08-22 13:14:42 -07:00
Hubert Lu
f445a1d9a3 [AMD] Fix Llama 4 FP8 accuracy issues on MI300X (#7699) 2025-08-22 13:13:45 -07:00
Kaixi Hou
e5638573c1 [NVIDA] [1/N] Nvfp4 Masked Gemm: Add quant op for the flashinfer grouped gemm (#9200) 2025-08-22 12:19:45 -07:00
Simo Lin
f556ac8bd8 [router] add json tool parser (#9516) 2025-08-22 12:13:04 -07:00
datdo-msft
110a65989b [MTP] Force greedy sampling on AMD (#9127) 2025-08-22 11:14:43 -07:00
Simo Lin
49f9d02538 [router] tokenizer arch doc (#9513) 2025-08-22 09:52:33 -07:00
Wenxuan Tan
0f587e80d3 Use Tensor Core Decode when gqa group size >= 4 (#8624)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-08-22 23:25:15 +08:00
huangtingwei
6078d5fcc0 [HiCacheStorage] backup optimization for MLA model (#8865)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-08-22 18:03:51 +08:00
pansicheng
70cf4abccc 3fs zerocopy (#9109)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-08-22 17:56:38 +08:00
Xuchun Shang
cebf45994b [bugfix] Make --enable-hierarchical-cache and --disable-radix-cache mutually exclusive (#9452)
Signed-off-by: Xuchun Shang <xuchun.shang@linux.alibaba.com>
2025-08-22 17:49:52 +08:00
Qiaolin Yu
9c0c1e30b2 Disable torch.compile for get_last_loc_large_page_size_large_top_k (#9507)
Co-authored-by: ispobock <ispobaoke@gmail.com>
2025-08-22 02:05:02 -07:00
Mick
a1f011d09a minor: determine mm attn backend based on platforms (#9303) 2025-08-22 01:08:41 -07:00
Qiaolin Yu
9ec314c6ac Support speculative decoding in the trtllm_mha attention backend (#9331)
Co-authored-by: ispobock <ispobaoke@gmail.com>
2025-08-21 23:53:35 -07:00
Xinyuan Tong
fedfe91c1a [Docs] Add doc and quick demo for gpt-oss responses api & buildin tools (#9497)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-21 23:51:52 -07:00
kk
988accbc1e Update docker file for supporting PD-Disaggregation on MI300x (#9494)
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: Colin Wang <kangwang@amd.com>
2025-08-21 23:48:40 -07:00
Yineng Zhang
b6b2287e4b chore: bump sgl-kernel v0.3.6.post2 (#9475) 2025-08-21 23:02:08 -07:00
Elfie Guo
243e745d07 Add trtllm_mla and cutlass_mla for ragged fmha for chunked prefill (#9480) 2025-08-21 23:01:36 -07:00
timmy-feng
61a0e600df torch.compile() mrope (#9487) 2025-08-21 23:01:08 -07:00
Simo Lin
0f8cee8cd3 [router] fix router load guard tracking for streaming (#9491) 2025-08-21 22:48:29 -07:00
Chang Su
816c4c8572 [router] add tool parser base structure and partial json parser (#9482) 2025-08-21 22:08:56 -07:00
Xinyuan Tong
13ec8d427e [Docs]Update reasoning parser doc & fix outdated link (#9492)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-21 22:08:28 -07:00
Chayenne
05bd789791 [docs]: fix reasoning context in docs (#9483) 2025-08-21 20:04:12 -07:00
kousakawang
5fd311d33e [code clean] add H20 cutlass groupGemm default config (#9333)
Co-authored-by: wanghanpei <wanghanpei@bytedance.com>
2025-08-21 19:23:29 -07:00
Chang Su
53e2cd464f [router] remove all tokenizer metrics for performance (#9474) 2025-08-21 18:35:24 -07:00
Yongfei Xu
9708d353b7 Support MHA with chunked prefix cache for flashinfer/flashmla backend, support page size > 1 for MHA chunked prefix (#8616)
Co-authored-by: xuyongfei.xyf <xuyongfei.xyf@antgroup.com>
2025-08-21 18:19:44 -07:00
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