Commit Graph

4004 Commits

Author SHA1 Message Date
kyleliang-nv
dd445a41f5 [feature] Add start step profile argument in /start_profile (#7608) 2025-07-09 18:42:15 -07:00
Shuaiyi Zhang
7590f5224b [router] Update metrics when request completes (#7899) 2025-07-09 08:18:09 -07:00
almaslof
f9df11ae86 Remove unused imports (#7898) 2025-07-09 22:36:48 +08:00
jianan-gu
d389bedf72 [CPU][Qwen3 MoE] Enable fused_topk CPU fusion and enhance FP8 TP padding (#7838) 2025-07-09 02:04:21 -07:00
Chunyuan WU
ac80f4da57 [CPU] [FP8] set SGLANG_CPU_FP8_CVT_FTZ in CMakeLists.txt (#7885) 2025-07-09 01:53:53 -07:00
Cheng Wan
d487555f84 [CI] Add deepep tests to CI (#7872) 2025-07-09 01:49:47 -07:00
Xinyuan Tong
e5888eddda Fixes typo in assertion message (#7895)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-07-09 01:47:14 -07:00
Yineng Zhang
066f4ec91f chore: bump v0.4.9.post1 (#7882) 2025-07-09 00:28:17 -07:00
Yineng Zhang
b6b6268ccf Revert "Embedding parallel by attn_tp (#7623)" (#7880) 2025-07-08 22:03:09 -07:00
Yikai Zhang
0870232195 Update native_api doc to match the change in the get_model_info endpoint (#7660)
Co-authored-by: Lifu Huang <lifu.hlf@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-07-08 21:05:58 -07:00
Shangming Cai
64c5907e12 [PD] Add guidance for prefill bootstrap timeout (#7846)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-07-08 21:00:34 -07:00
Chunyuan WU
128f16a817 [CPU]convert topk_weights to fp32 for INT8 and FP8 paths (for llama4) and fix LmHead weight pack (#7818) 2025-07-08 19:27:24 -07:00
ybyang
4986104618 Bump xgrammar's version to 0.1.20 (#7866) 2025-07-08 17:55:30 -07:00
Brayden Zhong
a37e1247c1 [Multimodal][Perf] Use pybase64 instead of base64 (#7724) 2025-07-08 14:00:58 -07:00
Xinyuan Tong
136c6e0431 fix: Handles input_embeds in GenerateReqInput when n>1 (#7830)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-07-08 14:00:42 -07:00
Xinyuan Tong
43e20c0647 Support Mimo-VL (#7579)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-07-08 14:00:25 -07:00
Xinyuan Tong
4bab50a6b5 Fix llama4 vision (#7840)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-07-08 14:00:03 -07:00
Xiaoyu Zhang
2e7ab862e3 Fix illegal memory in trtllm allreduce fusion (#7864) 2025-07-08 11:47:17 -07:00
Shuaiyi Zhang
51ae40306a [router] forward stream_options in request (#7860) 2025-07-08 08:03:38 -07:00
kk
653b873b91 Fix cache modules of triton import error (#7832) 2025-07-08 02:50:09 -07:00
Shangming Cai
d379bda4fa [Bugfix] Fix two batch overlap with auto DeepEP Dispatch (#7853)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-07-08 02:49:32 -07:00
Lifu Huang
2b0e1d1ce0 [Minor] Fix sporadic CI timeout caused by underestimated tests. (#7850) 2025-07-08 01:01:49 -07:00
Zhiyu
659907e32b Enable ModelOpt Llama4 fp8 checkpoint deployment in SGLang (#7129) 2025-07-08 00:19:50 -07:00
SijiaYang
cb9d91ea8a feat: support DeepSeek-R1-W4AFP8 model with ep-moe mode (#7762)
Signed-off-by: yangsijia.614 <yangsijia.614@bytedance.com>
2025-07-07 14:47:21 -07:00
Yineng Zhang
6a6e0bb7fd docs: update README (#7821) 2025-07-07 02:47:04 -07:00
Haohui Mai
076313bd09 [AMD] Fail gracefully when AITER is unavailable gfx90a GPUs (#7187) 2025-07-07 09:09:58 +00:00
Ziming Huang
9abe1163ac fix duplicate args in schedule_batch (#7816) 2025-07-07 01:31:03 -07:00
Simo Lin
3646f6bb3e [misc] release new router version (#7798) 2025-07-06 22:54:17 -07:00
Simo Lin
35724aa182 [docs] update router readme (#7797) 2025-07-06 22:54:11 -07:00
Zhiqiang Xie
2fc824b84c Kernels for efficient KV cache IO (#7313) 2025-07-06 22:53:36 -07:00
Yuan Luo
253454de9b Integrate triton moe kernel (#7689)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-07-06 20:05:49 -07:00
Simo Lin
ea3e7ffec7 [bugfix] Fix sgl-router get_server_info endpoint compatibility issue (#7813) 2025-07-06 19:52:57 -07:00
yuhsuan-t
8d4a01cbd7 Log the timestamps of each prefill/decode iteration (#6094)
Co-authored-by: yuhsuan-t <12108766+yuhsaun-t@users.noreply.github.com>
2025-07-07 01:57:27 +00:00
Ke Bao
a3398d8478 Optimize moe align block size kernel (#7794) 2025-07-07 09:20:30 +08:00
Nan Jiang
ba69c153f6 [RL]: Fix error tagging in multi-stage wake up (#7812)
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
2025-07-06 16:51:29 -07:00
Stefan He
3589aa79b0 [RL] Fix illegal memory for _import_static_state (#7733)
Co-authored-by: nanjiangwill <willjiang2018@gmail.com>
2025-07-06 16:25:21 -07:00
Hubert Lu
e00715eb66 [AMD] Add test_fused_moe.py and test_rope_rocm.py to AMD CI (#5246) 2025-07-06 01:47:16 -07:00
Lifu Huang
ea4bf12286 Fix division-by-zero bug in LoRA triton kernels. (#7785) 2025-07-06 00:45:29 -07:00
fzyzcjy
a291439a59 Support logprobs in two-batch overlap (#7709) 2025-07-05 19:05:32 -07:00
JieXin Liang
54411f6afa fix: disable dsv3_router_gemm in dsv3_nextn (#7793) 2025-07-05 19:01:01 -07:00
Yineng Zhang
625018d259 fix: free disk space (#7803) 2025-07-05 18:52:25 -07:00
Simo Lin
5732d904cc [misc] remove pdlb rust (#7796) 2025-07-05 17:44:51 -07:00
Yineng Zhang
ec5f9c6269 chore: bump v0.4.9 (#7802) 2025-07-05 17:40:29 -07:00
Yineng Zhang
62f5522ffe chore: upgrade sgl-kernel v0.2.4 (#7801) 2025-07-05 17:37:40 -07:00
Lifu Huang
01f9873048 Fix CI test OOM issue. (#7799) 2025-07-05 15:11:02 -07:00
Mick
199d621845 ci: fix port args (#7792) 2025-07-05 15:06:42 -07:00
Yineng Zhang
f200af0d8c chore: bump sgl-kernel v0.2.4 (#7800) 2025-07-05 15:03:31 -07:00
Lianmin Zheng
5589b75024 Add treemask mode to build_eagle_tree & release sgl-kernel 0.2.3 (#7756)
Co-authored-by: Pranjal Shankhdhar <pranjal.ssh@gmail.com>
2025-07-05 12:17:05 -07:00
JieXin Liang
c04a8a820b [fix] fix misusing of is_cuda (#7790) 2025-07-05 04:02:14 -07:00
Cheng Wan
6c903611ca Fix incorrect spec_num_draft_tokens in draft_extend (#7757) 2025-07-05 02:18:16 -07:00