Commit Graph

242 Commits

Author SHA1 Message Date
Lianmin Zheng
6406408a70 Clean up server_args.py (#7037) 2025-06-10 05:34:29 -07:00
Lianmin Zheng
dc0705a504 Simplify prepare_extend_after_decode (#6987) 2025-06-09 16:39:21 -07:00
ishandhanani
f1569876d5 feat: add direct routing strategy to DP worker (#6884) 2025-06-09 11:44:05 -07:00
Lianmin Zheng
20d3ad3b58 Fix CI and triton moe Configs (#6974) 2025-06-08 05:06:46 -07:00
fzyzcjy
f5599ef124 Refactor global_server_args_dict (#6866) 2025-06-07 03:10:35 -07:00
Cheng Wan
81964328b7 Set num_fused_shared_experts as num_shared_experts when shared_experts fusion is not disabled (#6736) 2025-06-04 15:53:22 -07:00
Xinyuan Tong
cf9815ba69 [Refactor] Multimodal data processing for VLM (#6659)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-06-04 11:22:33 -07:00
Cheng Wan
8a5480528d [Refactor] Rename n_share_experts_fusion as num_fused_shared_experts (#6735) 2025-06-03 17:48:24 -07:00
pansicheng
27e327b415 fix new_page_count_next_decode (#6671) 2025-06-02 22:48:52 -07:00
Lianmin Zheng
20fd53b8f6 Correctly abort the failed grammar requests & Improve the handling of abort (#6803) 2025-06-01 19:00:07 -07:00
YanbingJiang
888cb175a6 Add intel_amx backend for Radix Attention for CPU (#6408)
Co-authored-by: Chunyuan WU <chunyuan.wu@intel.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
2025-05-30 21:37:42 -07:00
JieXin Liang
2163586e63 [feat] triton kernel for get_last_loc (#6676) 2025-05-28 23:10:28 -07:00
fzyzcjy
0d47788025 Support overlapping two batches (#4068) 2025-05-24 17:39:07 -07:00
Byron Hsu
8233cc10fd [PD] Support logprob & Add failure test (#6558) 2025-05-23 14:29:20 -07:00
Chang Su
4685fbb888 [VLM] Support chunk prefill for VLM (#6355)
Co-authored-by: yizhang2077 <1109276519@qq.com>
2025-05-22 20:32:41 -07:00
Byron Hsu
0a4fc73b48 [PD] Fix failure abort (#6535) 2025-05-22 20:32:03 -07:00
fzyzcjy
ccfe5c009d Support redundant experts in expert parallel (#6461) 2025-05-21 02:05:53 -07:00
fzyzcjy
e98afbe042 Support dispatching logical to physical experts (#6385) 2025-05-19 22:13:55 -07:00
Mick
626ccb7d3f vlm: tensor hash kernel (#5974) 2025-05-18 15:38:16 -07:00
Mick
01dd39bac1 refactor: minor refactors regarding multimodal processing (#6187) 2025-05-17 22:53:20 -07:00
fzyzcjy
fd08c04821 Support custom DeepEP tuning config (#6257) 2025-05-17 17:09:42 -07:00
Yury Sulsky
f19a9204cd Support precomputed multimodal features for Qwen-VL and Gemma3 models. (#6136)
Co-authored-by: Yury Sulsky <ysulsky@tesla.com>
2025-05-16 12:26:15 -07:00
Lianmin Zheng
d18c6b3358 Support incremental streaming of logprob/token_ids between scheduler and detokenizer (#6225)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
2025-05-12 14:33:38 -07:00
Cheng Wan
25c83fff6a Performing Vocabulary Parallelism for LM Head across Attention TP Groups (#5558)
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
2025-05-11 23:36:29 -07:00
Lianmin Zheng
01bdbf7f80 Improve structured outputs: fix race condition, server crash, metrics and style (#6188) 2025-05-11 08:36:16 -07:00
Yusong Gao
41273fd71f fix: handle None multimodal_inputs during merging and filtering batches in disaggregation decode mode (#6169) 2025-05-11 00:28:21 -07:00
applesaucethebun
2ce8793519 Add typo checker in pre-commit (#6179)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
2025-05-11 12:55:00 +08:00
Lianmin Zheng
de167cf5fa Fix request abortion (#6184) 2025-05-10 21:54:46 -07:00
yhyang201
cec98f1034 [Fix] Incorrect Memory Allocation on CUDA:0 by Non-Zero CUDA Processes in TP/DP (#5745) 2025-05-08 17:52:26 -07:00
Ying Sheng
11383cec3c [PP] Add pipeline parallelism (#5724) 2025-04-30 18:18:07 -07:00
Trevor Morris
84810da4ae Add Cutlass MLA attention backend (#5390) 2025-04-27 20:58:53 -07:00
Liangsheng Yin
40d9b8acce Improve overlap scheduling (#5788) 2025-04-28 11:19:16 +08:00
Yi Zhang
1f963d7f64 Bugfix for minicpmo vision test (#5760) 2025-04-26 23:18:02 +08:00
Mick
feda9b11b3 fix: fix one more bug from merging mm_inputs (#5718)
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: XinyuanTong <115166877+JustinTong0323@users.noreply.github.com>
2025-04-25 17:28:33 -07:00
IAN
11e27d0926 [PD]: Support Muti Prefill in one node (#5704)
Co-authored-by: shuaills <shishuaiuoe@gmail.com>
2025-04-26 00:30:47 +08:00
Mick
c998d04b46 vlm: enable radix cache for qwen-vl models (#5349)
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
2025-04-23 20:35:05 -07:00
Byron Hsu
bf98d2e377 [PD] Support prefill overlap + Ensure no race condition (#5609) 2025-04-21 12:12:56 -07:00
Zhiqiang Xie
70645f4d7d upstream hicache fixes (#5570) 2025-04-20 23:08:30 -07:00
Xiaoyu Zhang
d58e354472 simplify the control logic for using shared experts fusion (#5504) 2025-04-19 13:17:35 -07:00
fzyzcjy
53dcf38876 Introduce moe_dense_tp_size to fix dense layer errors in DeepSeek V3 + 4x8xH100 (#4836) 2025-04-17 21:38:26 -07:00
Baizhou Zhang
6fb29ffd9e Deprecate enable-flashinfer-mla and enable-flashmla (#5480) 2025-04-17 01:43:33 -07:00
Baizhou Zhang
4fb05583ef Deprecate disable-mla (#5481) 2025-04-17 01:43:14 -07:00
Baizhou Zhang
a42736bbb8 Support MHA with chunked prefix cache for DeepSeek chunked prefill (#5113) 2025-04-15 22:01:22 -07:00
Byron Hsu
a9499885e9 [PD] Add transfer backend abstraction (#5328) 2025-04-14 01:39:39 +08:00
Mick
34ef6c8135 [VLM] Adopt fast image processor by default (#5065) 2025-04-11 21:46:58 -07:00
Mick
e53a0b3d5b [fix] fix mrope positions not picked up (#5265) 2025-04-11 01:29:45 -07:00
Teng Ma
4c31ae9f6d [PD] Support KV transfer with mooncake (#4880)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
Co-authored-by: Shangming Cai <caishangming@linux.alibaba.com>
Co-authored-by: Xuchun Shang <xuchun.shang@linux.alibaba.com>
Co-authored-by: shangmingc <csmthu@gmail.com>
2025-04-10 14:23:23 +08:00
Stefan He
5db37c8626 [metrics] Add in queue metrics (#4444) 2025-04-09 17:19:27 -07:00
Mick
fbebcb7aa4 model: support mllama4 (#5144) 2025-04-09 09:28:44 -07:00
fzyzcjy
466899e69c Fix multimodal hashing error (#5174) 2025-04-08 18:42:26 -07:00