4867 Commits

Author SHA1 Message Date
Kaixi Hou
27a09dc52c
[NVIDIA] Fix an issue to use current stream for the nvfp4 quant (#13632) 2025-02-20 22:01:48 -08:00
Edwin Hernandez
981f3c831e
[Misc] Adding script to setup ray for multi-node vllm deployments (#12913) 2025-02-20 21:16:40 -08:00
Kante Yin
44c33f01f3
Add llmaz as another integration (#13643)
Signed-off-by: kerthcet <kerthcet@gmail.com>
2025-02-21 03:52:40 +00:00
Lingfan Yu
33170081f1
[Neuron][Kernel] Vectorize KV cache load in FlashPagedAttention to maximize DMA bandwidth (#13245)
Signed-off-by: Lingfan Yu <lingfany@amazon.com>
2025-02-20 17:45:45 -08:00
Michael Goin
71face8540
[Bugfix] Fix max_num_batched_tokens for MLA (#13620)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-02-20 17:45:20 -08:00
Joe Runde
bfbc0b32c6
[Frontend] Add backend-specific options for guided decoding (#13505)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2025-02-20 15:07:58 -05:00
ajayvohra2005
6a417b8600
fix neuron performance issue (#13589) 2025-02-20 10:59:36 -08:00
Woosuk Kwon
d3ea50113c
[V1][Minor] Print KV cache size in token counts (#13596)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-20 09:24:31 -08:00
Harry Mellor
34aad515c8
Update pre-commit's isort version to remove warnings (#13614) 2025-02-20 08:00:14 -08:00
chenxiaobing
ed6e9075d3
[Bugfix] Fix deepseekv3 grouped topk error (#13474)
Signed-off-by: Chen-XiaoBing <chenxb002@whu.edu.cn>
v0.7.3
2025-02-20 06:47:01 -08:00
Harry Mellor
992e5c3d34
Merge similar examples in offline_inference into single basic example (#12737) 2025-02-20 04:53:51 -08:00
Varun Sundar Rabindranath
b69692a2d8
[Kernel] LoRA - Refactor sgmv kernels (#13110) 2025-02-20 07:28:06 -05:00
Kevin H. Luu
a64a84433d
[2/n][ci] S3: Use full model path (#13564)
Signed-off-by: <>
2025-02-20 01:20:15 -08:00
Kevin H. Luu
aa1e62d0db
[ci] Fix spec decode test (#13600) 2025-02-20 16:56:00 +08:00
Michael Goin
497bc83124
[CI/Build] Use uv in the Dockerfile (#13566) 2025-02-19 23:05:44 -08:00
Yuan Tang
3738e6fa80
[API Server] Add port number range validation (#13506)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
2025-02-20 15:05:13 +08:00
Gregory Shtrasberg
0023cd2b9d
[ROCm] MI300A compile targets deprecation (#13560) 2025-02-19 23:05:00 -08:00
041e294716
[Misc] add mm_processor_kwargs to extra_body for Qwen2.5-VL (#13533) 2025-02-19 23:04:30 -08:00
Alex Brooks
9621667874
[Misc] Warn if the vLLM version can't be retrieved (#13501)
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
2025-02-20 06:24:48 +00:00
Simon Mo
8c755c3b6d
[bugfix] spec decode worker get tp group only when initialized (#13578) 2025-02-20 04:46:28 +00:00
youkaichao
ba81163997
[core] add sleep and wake up endpoint and v1 support (#12987)
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: cennn <2523403608@qq.com>
Co-authored-by: cennn <2523403608@qq.com>
2025-02-20 12:41:17 +08:00
Divakar Verma
0d243f2a54
[ROCm][MoE] mi300 mixtral8x7B perf for specific BS (#13577)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
2025-02-20 04:01:02 +00:00
Kevin H. Luu
88f6ba3281
[ci] Add AWS creds for AMD (#13572) 2025-02-20 03:56:06 +00:00
Jee Jee Li
512368e34a
[Misc] Qwen2.5 VL support LoRA (#13261) 2025-02-19 18:37:55 -08:00
Kevin H. Luu
473f51cfd9
[3/n][CI] Load Quantization test models with S3 (#13570)
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
2025-02-20 10:12:30 +08:00
Nick Hill
a4c402a756
[BugFix] Avoid error traceback in logs when V1 LLM terminates (#13565)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-02-20 00:49:01 +00:00
Isotr0py
550d97eb58
[Misc] Avoid calling unnecessary hf_list_repo_files for local model path (#13348)
Signed-off-by: isotr0py <2037008807@qq.com>
2025-02-19 18:57:48 +00:00
Cody Yu
fbbe1fbac6
[MISC] Logging the message about Ray teardown (#13502)
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Rui Qiao <161574667+ruisearch42@users.noreply.github.com>
2025-02-19 09:40:50 -08:00
Wilson Wu
01c184b8f3
Fix copyright year to auto get current year (#13561) 2025-02-19 16:55:34 +00:00
youkaichao
ad5a35c21b
[doc] clarify multi-node serving doc (#13558)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-19 22:32:17 +08:00
shangmingc
5ae9f26a5a
[Bugfix] Fix device ordinal for multi-node spec decode (#13269)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-02-19 22:13:15 +08:00
Cyrus Leung
377d10bd14
[VLM][Bugfix] Pass processor kwargs properly on init (#13516)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-02-19 13:13:50 +00:00
youkaichao
52ce14d31f
[doc] clarify profiling is only for developers (#13554)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-02-19 20:55:58 +08:00
Daniele
81dabf24a8
[CI/Build] force writing version file (#13544)
Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com>
2025-02-19 18:48:03 +08:00
Yannick Schnider
423330263b
[Feature] Pluggable platform-specific scheduler (#13161)
Signed-off-by: Yannick Schnider <yannick.schnider1@ibm.com>
Signed-off-by: Yannick Schnider <Yannick.Schnider1@ibm.com>
2025-02-19 17:16:38 +08:00
Nick Hill
caf7ff4456
[V1][Core] Generic mechanism for handling engine utility (#13060)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-02-19 17:09:22 +08:00
Lucia Fang
f525c0be8b
[Model][Speculative Decoding] DeepSeek MTP spec decode (#12755)
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-02-19 17:06:23 +08:00
Alex Brooks
983a40a8bb
[Bugfix] Fix Positive Feature Layers in Llava Models (#13514)
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
2025-02-19 08:50:07 +00:00
Zhe Zhang
fdc5df6f54
use device param in load_model method (#13037) 2025-02-19 16:05:02 +08:00
Kevin H. Luu
3b05cd4555
[perf-benchmark] Fix ECR path for premerge benchmark (#13512)
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
2025-02-19 07:56:11 +00:00
Kevin H. Luu
d5d214ac7f
[1/n][CI] Load models in CI from S3 instead of HF (#13205)
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
2025-02-19 07:34:59 +00:00
Roger Wang
fd84857f64
[Doc] Add clarification note regarding paligemma (#13511) 2025-02-18 22:24:03 -08:00
Divakar Verma
8aada19dfc
[ROCm][MoE configs] mi325 mixtral & mi300 qwen_moe (#13503) 2025-02-18 22:23:24 -08:00
Kevin H. Luu
9aa95b0e6a
[perf-benchmark] Allow premerge ECR (#13509)
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
2025-02-19 05:13:41 +00:00
Yu-Zhou
d0a7a2769d
[Hardware][Gaudi][Feature] Support Contiguous Cache Fetch (#12139)
Signed-off-by: yuzhou <yuzhou@habana.ai>
Signed-off-by: zhouyu5 <yu.zhou@intel.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2025-02-18 19:40:19 -08:00
Harry Mellor
00b69c2d27
[Misc] Remove dangling references to --use-v2-block-manager (#13492)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-02-19 03:37:26 +00:00
Woosuk Kwon
4c82229898
[V1][Spec Decode] Optimize N-gram matching with Numba (#13365)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-18 13:19:58 -08:00
Woosuk Kwon
c8d70e2437
Pin Ray version to 2.40.0 (#13490)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-02-18 12:50:31 -08:00
Nick Hill
30172b4947
[V1] Optimize handling of sampling metadata and req_ids list (#13244)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-02-18 12:15:33 -08:00
Murali Andoorveedu
a4d577b379
[V1][Tests] Adding additional testing for multimodal models to V1 (#13308)
Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
2025-02-18 09:53:14 -08:00