Skip to content

Pull Upstream main 6/16 #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 878 commits into from
Jun 16, 2025
Merged

Pull Upstream main 6/16 #7

merged 878 commits into from
Jun 16, 2025

Conversation

amogkam
Copy link
Collaborator

@amogkam amogkam commented Jun 16, 2025 •
edited by github-actions bot
Loading

No description provided.

youkaichao and others added 30 commits June 3, 2025 21:42
@youkaichao
[doc] clarify windows support (vllm-project#19088)
4e88723 
Signed-off-by: youkaichao <youkaichao@gmail.com>
@jeejeelee
[CI/Build] Remove V0 LoRA test (vllm-project#19066)
4e68ae5 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
@hmellor
Fix underscores in dict keys passed via CLI (vllm-project#19030)
476844d 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
@zucchini-nlp
[Bugfix] disable processor cache (vllm-project#19068)
d81edde 
Signed-off-by: raushan <raushan@huggingface.co>
@houseroad
[Doc] Improve the Pull Request template with key components (vllm-pro…
d00dd65 
…ject#19086)

Signed-off-by: Lu Fang <lufang@fb.com>
@NickLucche
[Misc] Add missing _Backend enums (vllm-project#19081)
4b7817c 
Signed-off-by: nicklucche <nlucches@redhat.com>
@googs1025
[Misc] fix: add miss best_of param validation (vllm-project#18555)
d054da1 
Signed-off-by: googs1025 <googs1025@gmail.com>
@simon-mo
[Misc] Add SPDX-FileCopyrightText (vllm-project#19100)
02f0c7b 
Signed-off-by: simon-mo <simon.mo@hey.com>
@SorenDreano @SorenNumind
[Doc] Readme standardization (vllm-project#18695)
19bdaf3 
Co-authored-by: Soren Dreano <soren@numind.ai>
@reidliu41
[doc] update docker version (vllm-project#19074)
01eee40 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
@varun-sundar-rabindranath
[Kernel] DeepEP dispatch-combine kernel integration (vllm-project#18434)
fa98d77 
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
@sarckk
[V1] Support cross-layer KV sharing (vllm-project#18212)
bdf1396 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
@mgoin
[Perf] Tune scaled_fp8_quant by increasing vectorization (vllm-proj…
e31446b 
…ect#18844)

Signed-off-by: mgoin <mgoin64@gmail.com>
@hmellor @Yikun
Fix interaction between Optional and Annotated in CLI typing (vll…
6865fe0 
…m-project#19093)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Yikun Jiang <yikun@apache.org>
@heheda12345
[v1] Re-init input batch for multiple kv cache groups (vllm-project#1…
6cac54f 
…8654)

Signed-off-by: Chen Zhang <zhangch99@outlook.com>
@ekagra-ranjan
[V1][Spec Decode][Ngram] 1.35x gain -> 1.95x gain on InstructCoder wi…
135cf55 
…th prompt fix (vllm-project#18971)
@heheda12345
[Bugfix] get_num_blocks_to_allocate with null_block (vllm-project#19031)
b5fd950 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
@chaunceyjiang
[Bugfix]: Fix the incompatibility issue with tool_choice 'required' w…
4de790f 
…hen Thinking is enabled (vllm-project#19075)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
@NickLucche @robertgshaw2-redhat
[Bugfix][P/D] Fix Prefix Cache Bug (vllm-project#18411)
5d96533 
Signed-off-by: nicklucche <nlucches@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
@heheda12345
[Bugfix] Max concurrency estimation and check_enough_kv_cache_memory …
a8da78e 
…for models with sliding window layers (vllm-project#19029)

Signed-off-by: Chen Zhang <zhangch99@outlook.com>
@PeaBrane
feat: add data parallel rank to KVEventBatch (vllm-project#18925)
b712be9
@Jeffwan
[Misc] Fix path and python alias errors in disagg_prefill exmaples (v…
abd7df2 
…llm-project#18919)
@russellb @markmc @DarkLight1337
[Docs] Add developer doc about CI failures (vllm-project#18782)
52dceb1 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
@bigPYJ1151
[CPU] V1 support for the CPU backend (vllm-project#16441)
4555143
@lgeiger
[Core] Cast multimodal input in hf processor (vllm-project#18862)
1409ef9 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
@vadiklyutiy
[KERNEL] Sampler. CUDA kernel for applying repetition penalty (vllm-p…
5d6d1ad 
…roject#18437)
@calvin0327
[Cleanup][v1]:remote guided-decoding-backend for example (vllm-projec…
8d646c2 
…t#19059)

Signed-off-by: calvin chen <120380290@qq.com>
@kaixih
[NVIDIA] Add Cutlass MLA backend (vllm-project#17625)
41aa578
@WoosukKwon
[Bugfix] Fix FA3 full cuda graph correctness (vllm-project#19106)
b124e10 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
@princepride
Fix vllm-project#19130 (vllm-project#19132)
3336c8c 
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
kzawora-intel and others added 28 commits June 14, 2025 12:30
@kzawora-intel
[Bugfix] Don't attempt to use triton if no driver is active (vllm-pro…
861a0a0 
…ject#19561)
@maobaolong
[Fix] Convert kv_transfer_config from dict to KVTransferConfig (vllm-…
0850001 
…project#19262)
@ilmarkov
[Perf] Further tunings for SM100 FP8 CUTLASS kernel (vllm-project#19566)
e13945f
@houseroad
[Bugfix][2/n] Fix speculative decoding CI - Fix test_ngram_e2e_greedy…
ee1531b 
…_correctness (vllm-project#19644)
@22quinn
[Kernel] Raise verbose error and consolidate num_heads/num_kv_heads…
0b73736 
… divisibility check (vllm-project#19339)

Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
@yewentao256
[Benchmark] Refactor benchmark script for fp8 & int8 (vllm-project#19627
3d330c4 
)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
@WoosukKwon
Enable prefix caching with full cuda graphs (vllm-project#19617)
055915e 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
@zou3519
[CI/Build] Fix torch nightly CI dependencies part 2 (vllm-project#19589)
91b2c17
@Isotr0py
[Misc] Remove duplicate multiproc method setting for CPU platform (vl…
a5e7242 
…lm-project#19649)

Signed-off-by: Isotr0py <2037008807@qq.com>
@houseroad
[MISC] Remove unused variableds in C++ (vllm-project#19609)
c6703d1 
Signed-off-by: Lu Fang <lufang@fb.com>
@quanliu1991
[Bugfix][Core] Prefix caching causes incorrect outputs due to outdate…
92183b4 
…d ComputedBlocksTracker (vllm-project#18957)

Signed-off-by: 刘全 <quan.liu2@dbappsecurity.com.cn>
Co-authored-by: 刘全 <quan.liu2@dbappsecurity.com.cn>
@f14-bertolotti @francesco-bertolotti @aarnphm
[Misc][Frontend] passthrough bad_words (vllm-project#19564)
367871a 
Signed-off-by: Francesco Bertolotti <francesco.bertolotti@igenius.ai>
Co-authored-by: Francesco Bertolotti <francesco.bertolotti@igenius.ai>
Co-authored-by: Aaron Pham <Aaronpham0103@gmail.com>
@yeqcharlotte
[Misc] Fix skipped max-model-len validation when deriving max model l…
b692e9c 
…ength from tokenizer config (vllm-project#19660)

Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
@yaochengji @mgoin
[TPU] support attention head dim smaller than 128 (vllm-project#19620)
a77aea5 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
@andyxning
[MISC] typo fix (vllm-project#19672)
26bc46e 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
@noooop
[CI] Add mteb testing for rerank models (vllm-project#19344)
f40f763
@russellb
[Docs] Move multiproc doc to v1 dir (vllm-project#19651)
8d12070 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
@SzymonOzog
[Kernel] GGUF MMVQ kernel for multiple input vectors (vllm-project#18754
dec66d2 
)

Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
@njhill
[BugFix] Don't catch BaseException when dumping execute_model errors (v…
ee35e96 
…llm-project#19626)

Signed-off-by: Nick Hill <nhill@redhat.com>
@Navanit-git
[DOC] Add reasoning capability to vLLM streamlit code (vllm-project#1…
3e75069 
…9557)
@shawntan
[Feature]:Allow for Granite MoE Hybrid models with _only_ shared expe…
4d54240 
…rts. (vllm-project#19652)

Signed-off-by: Shawn Tan <shawntan@ibm.com>
@Isotr0py
[Bugfix] Fix TP inference for Flex attention backend (vllm-project#19657
1173804 
)

Signed-off-by: Isotr0py <2037008807@qq.com>
@andyxning
[MISC] bump huggingface_hub pkg to 0.33.0 (vllm-project#19547)
c3fec47 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
@chaunceyjiang
[Bugfix] fix missing 'finish_reason': null in streaming chat (vllm-pr…
836d4ce 
…oject#19662)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
@bnellnm
[Kernels] Use empty for modular MoE workspaces (vllm-project#19667)
5e5baa9 
Signed-off-by: Bill Nell <bnell@redhat.com>
@qscqesze
[Model] Add support for MiniMaxM1ForCausalLM (shares architecture wit…
387bdf0 
…h MiniMaxText01ForCausalLM) (vllm-project#19677)

Signed-off-by: QscQ <qscqesze@gmail.com>
@russellb
[V1] Change return type on get_multimodal_embeddings() (vllm-project#…
90f9c2e 
…19446)

Signed-off-by: Russell Bryant <rbryant@redhat.com>
@amogkam
Merge branch 'main' of github.com:vllm-project/vllm
eb059d5
@amogkam amogkam requested a review from simon-mo as a code owner June 16, 2025 19:17
@amogkam amogkam merged commit add726d into main Jun 16, 2025
1 of 4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@simon-mo simon-mo Awaiting requested review from simon-mo simon-mo is a code owner

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.