xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-26 05:35:51 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,510 Commits 155 Branches 89 Tags
Commit Graph

12510 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
majiayu000
abd1dbc548 [Bugfix] Preserve original tokenizer class name in CachedTokenizer 
HuggingFace transformers processor validates tokenizer type by checking
the class name. When vLLM creates a CachedTokenizer with a modified
class name (e.g., 'CachedQwen2TokenizerFast'), the processor type check
fails with TypeError.

This fix preserves the original tokenizer class name and qualname in
CachedTokenizer, ensuring compatibility with HuggingFace transformers
processor type checking.

Fixes #31080

Signed-off-by: Claude <noreply@anthropic.com>
Signed-off-by: majiayu000 <1835304752@qq.com>
 2025-12-24 16:02:48 +08:00
Ryan Rock
ddfac7034e
[CI/Build] Ignore data_parallel_size_local (#30281) 
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
 2025-12-24 07:40:54 +00:00
Micah Williamson
6559d96796
[ROCm][CI] Set TORCH_NCCL_BLOCKING_WAIT Distributed Tests On ROCm (#31259) 
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
 2025-12-24 07:19:07 +00:00
kliuae
1c74150bca
[ROCm][CI] Fix "Distributed Tests (H200)" Test (#31227) 
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
 2025-12-24 06:56:30 +00:00
Andreas Karatzas
0247a91e00
[ROCm][CI] Fix entrypoints tests and Python-only installation test on ROCm (#28979) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2025-12-23 22:42:30 -08:00
Michael Goin
8ee90c83f8
Add --max-model-len auto to auto-fit context to available memory (#29431) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-12-23 21:37:14 -08:00
Nick Cao
d7e05ac743
[docker] Fix downloading sccache on aarch64 platform (#30070) 
Signed-off-by: Nick Cao <nickcao@nichi.co>
 2025-12-23 21:36:33 -08:00
sihao_li
471ddb99a0
[XPU] Remove distributed_executor_backend check (#30760) 
Signed-off-by: sihao.li <sihao.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-12-23 21:34:33 -08:00
Xiong Wang
bb24592d13
[Qwen3-Omni] fixed _get_feat_extract_output_lengths function (#31007) 
Signed-off-by: Xiong Wang <wangxiongts@163.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-12-23 21:33:54 -08:00
Matthew Bonanni
369f47aa0f
[DeepSeek v3.2] Remove unnecessary syncwarps (#31047) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-12-23 21:33:30 -08:00
zejunchen-zejun
dabff12ed3
[Bugfix][ROCm][Dynamo][DS 3.1][FP8] fix unsupported hasattr call when Dynamo tracing for ROCm device (#31149) 
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
 2025-12-23 21:32:19 -08:00
Ming Yang
3bb9561928
Revert "[bench] Support common prefix len config (for decode-only bench)" (#31240) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
 2025-12-23 21:17:23 -08:00
Micah Williamson
3ce791ac77
[ROCm][CI] Set VLLM_FLOAT32_MATMUL_PRECISION="tf32" For terratorch Tests In AMD CI (#31242) 
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
 2025-12-24 03:21:50 +00:00
Andreas Karatzas
e42894f5b5
[ROCm][CI][Bugfix] Fix Siglip2 rotary embedding dispatch and InternVL video test tolerance (#31235) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2025-12-24 02:56:58 +00:00
Wentao Ye
76e6a95192
[Bug] Fix Number of dimensions of tensors must match. for Deepseek V3.2 (#31160) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-24 10:41:09 +08:00
Chao Lei
8b59753cdb
[P/D] Mooncake connector support more protocols (#30133) 
Signed-off-by: LCAIZJ <leichao139636@163.com>
 2025-12-24 10:24:07 +08:00
Chen Zhang
538e830caa
[KVEvent] User request.block_hash for parent block_hash (#30544) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Co-authored-by: Yifan Qiao <yifanqiao@berkeley.edu>
 2025-12-23 18:23:43 -08:00
rongfu.leng
4ed11105d7
[Misc] Remove unused custom ops copy_blocks and copy_blocks_mla (#30967) 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
 2025-12-23 18:22:35 -08:00
Cyrus Leung
dd424571c8
[Bugfix] Enable dynamic_dims for different embeds shape (#31223) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-24 10:15:47 +08:00
Cyrus Leung
ca6a95ba25
[Chore] Simplify logic of _execute_mm_encoder (#31222) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-23 18:15:16 -08:00
Vadim Gimpelson
bc0a5a0c08
[CI] Add Qwen3-Next-FP8 to Blackwell model tests (#31049) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
 2025-12-23 17:21:50 -08:00
Andreas Karatzas
bfa2c0bbb9
[ROCm][Bugfix] Fix RuntimeError in MMEncoderAttention by replacing .view() with .reshape() (#31203) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2025-12-23 21:48:01 +00:00
Mark McLoughlin
f790068600
[Core] Add a random suffix to frontend-provided request IDs (#27987) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2025-12-23 13:05:39 -08:00
Asaf Joseph Gardin
34916ae37f
[Mamba] - Consolidate Mambas Attention Logic (#28133) 2025-12-23 21:57:00 +01:00
Yuan Tang
0736f901e7
docs: Add llm-d integration to the website (#31234) 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
 2025-12-23 20:27:22 +00:00
Harry Mellor
c016c95b45
Use helper function instead of looping through attribute names (#29788) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-23 17:31:56 +00:00
Harry Mellor
1339878e13
Only patch original_max_position_embeddings for Transformers v4 (#31214) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-23 16:46:32 +00:00
danielafrimi
b94f80ffb8
[FIX] FP4 quantization kernel padding initialization bug (#31097) 
Signed-off-by: <>
Co-authored-by: root <root@gpu-193.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: root <root@gpu-951.slurm-workers-slurm.slurm.svc.cluster.local>
 2025-12-23 08:45:18 -08:00
Joachim Studnia
38c361f99d
Fix edge case Mistral tool parser (#30724) 
Signed-off-by: Joachim Studnia <joachim@mistral.ai>
Signed-off-by: Joachim Studnia <studniajoachim@gmail.com>
Signed-off-by: juliendenize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: juliendenize <julien.denize@mistral.ai>
Co-authored-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2025-12-23 14:19:58 +00:00
Cyrus Leung
bb62dda2c3
[Misc] Introduce encode_*_url utility function (#31208) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-23 13:45:21 +00:00
Patrick von Platen
3faa8bee57
adapt voxtral (#31095) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2025-12-23 05:31:55 -08:00
Harry Mellor
b10d47e0e0
Add util function for checking nesting of rope parameters (#31146) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-23 11:41:49 +00:00
R3hankhan
769f27e701
[OpenAI] Add parameter metadata to validation errors (#30134) 
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
 2025-12-23 11:30:12 +00:00
Jakub Zakrzewski
23daef548d
[Frontend] Support using chat template as custom score template for reranking models (#30550) 
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
 2025-12-23 11:19:16 +00:00
Jee Jee Li
27c6c2f98c
[Bugfix] Fix MoE LoRA bin/pt loading (#31161) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-12-23 19:09:15 +08:00
Weida Hong
73cfb7a722
Correct position of docstring of class attributes (#31209) 
Signed-off-by: Weida Hong <wdhongtw@google.com>
 2025-12-23 02:08:58 -08:00
vllmellm
f32cfd7d97
[ROCm][FEAT] Support AITER RMSNorm quantization fusion pass (#26575) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2025-12-23 02:07:54 -08:00
Jee Jee Li
6b16fff01b
[Bugfix] Fix Jais2ForCausalLM (#31198) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-12-23 07:44:01 +00:00
Yan Ma
f1c2c20136
[XPU] decrease IGC_ForceOCLSIMDWidth for speculative decoding triton-xpu kernel compilation (#30538) 
Signed-off-by: Yan Ma <yan.ma@intel.com>
 2025-12-23 05:22:15 +00:00
Cyrus Leung
8cef137689
[Chore] Update more locations to use attention_config.backend (#31153) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-22 19:19:50 -08:00
quanliu
a37328fc5c
[Feature] Batch invariant: Lora (#30097) 
Signed-off-by: quanliu <18646313696@163.com>
 2025-12-23 10:32:47 +08:00
Pavani Majety
3e10262356
Revert "[SM100] Enable fp8 compute for prefill MLA (#30746)" (#31197) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
 2025-12-22 18:15:33 -08:00
Angela Yi
612d5ffdab
[ci] Fix Pytorch compilation test oom in 2.10 (#31194) 
Signed-off-by: angelayi <yiangela7@gmail.com>
 2025-12-23 01:56:47 +00:00
Divakar Verma
78e5e62bbf
[AMD][CI] fix v1/engine test_preprocess_error_handling (#31192) 
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
 2025-12-23 01:28:19 +00:00
Robert Shaw
b57b967386
[MoE Refactor][7/N] AITER MK (#31102) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2025-12-22 16:42:58 -07:00
Michael Goin
6d518ffbaa
[CI Failure] Disable mosaicml/mpt-7b and databricks/dbrx-instruct tests (#31182) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-12-22 15:40:35 -08:00
Benjamin Chislett
85aff45e24
[Perf] Remove blocking copy in GDN Attention (#31167) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
 2025-12-22 14:25:22 -08:00
Wentao Ye
5312a7284e
[Bug] Fix 'CutlassMLAImpl' object has no attribute '_workspace_buffer' (#31173) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-22 14:24:27 -08:00
Lucas Wilkinson
de71747655
[SpecDecode] Simplified alternative padded-speculation acceptance rate fix (#29845) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-22 13:06:10 -08:00
Michael Goin
9586354053
[Doc] Add vllm-metal to hardware plugin documentation (#31174) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-12-22 20:06:29 +00:00