Skip to content

Upstream merge 2025 05 27 #557

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 195 commits into from
May 27, 2025
Merged

Upstream merge 2025 05 27 #557

merged 195 commits into from
May 27, 2025

Conversation

gshtras
Copy link
Collaborator

@gshtras gshtras commented May 27, 2025

No description provided.

sunyicode0012 and others added 30 commits May 19, 2025 09:49
@sunyicode0012
Add files via uploadAdd fused MoE kernel tuning configs (fp8_w8a8) fo…
7937c2f 
…r DeepSeek V3/R1 on a single-node 8x NVIDIA H20 96GB setup (vllm-project#18337)
@Unprincess17
[Misc] Fix typo (vllm-project#18330)
8171221
@aws-satyajith
Neuron up mistral (vllm-project#18222)
dc1440c 
Signed-off-by: Satyajith Chilappagari <[email protected]>
@luccafong
fix CUDA_check redefinition in vllm-project#17918 (vllm-project#18287)
258bf62 
Signed-off-by: Lucia Fang <[email protected]>
Co-authored-by: Lucia (Lu) Fang <[email protected]>
@liangfu
[neuron] fix authorization issue (vllm-project#18364)
d565e09 
Signed-off-by: Liangfu Chen <[email protected]>
@Isotr0py
[Misc] Allow AutoWeightsLoader to skip loading weights with specifi…
f07a673 
…c substr in name (vllm-project#18358)

Signed-off-by: Isotr0py <[email protected]>
@Nan2018 @qthequartermasterman
[Core] [Bugfix]: tensor parallel with prompt embeds (vllm-project#18171)
9609327 
Signed-off-by: Nan2018 <[email protected]>
Co-authored-by: Andrew Sansom <[email protected]>
@khluu
[release] Change dockerhub username for TPU release (vllm-project#18389)
d981396
@rand-fly
[Bugfix] fix adding bias twice in ipex GPTQ quantization (vllm-projec…
bca55b5 
…t#18363)

Signed-off-by: rand-fly <[email protected]>
@reidliu41
[doc] update env variable export (vllm-project#18391)
1b1e8e0 
Signed-off-by: reidliu41 <[email protected]>
Co-authored-by: reidliu41 <[email protected]>
@jeejeelee
[Misc] Add LoRA code owner (vllm-project#18387)
6b35cb1 
Signed-off-by: Jee Jee Li <[email protected]>
@princepride
Update cpu.txt (vllm-project#18398)
d6c86d0 
Signed-off-by: 汪志鹏 <[email protected]>
@noooop
[CI] Add mteb testing to test the accuracy of the embedding model (vl…
8684770 
…lm-project#17175)
@wulipc
[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure T…
be48360 
…ext (vllm-project#18407)

Co-authored-by: 松灵 <[email protected]>
@reidliu41
[Misc] refactor prompt embedding examples (vllm-project#18405)
8f55962 
Signed-off-by: reidliu41 <[email protected]>
Co-authored-by: reidliu41 <[email protected]>
@mgoin
[Minor] Rename quantization nvfp4 to modelopt_fp4 (vllm-project#18356)
f4a8a37 
Signed-off-by: mgoin <[email protected]>
@calvin0327
[Model] use AutoWeightsLoader for bloom (vllm-project#18300)
e1f5a71 
Signed-off-by: calvin chen <[email protected]>
@haochengxia
[Kernel] update comment for KV shape in unified triton attn (vllm-pro…
980a172 
…ject#18099)

Signed-off-by: haochengxia <[email protected]>
@dilipgb
fix:Build torch wheel inline rather than picking from nightly (vllm-p…
23baa21 
…roject#18351)

Signed-off-by: Dilip Gowda Bhagavan <[email protected]>
@mgoin
[TPU] Re-enable the Pallas MoE kernel (vllm-project#18025)
3b17ea2 
Signed-off-by: Michael Goin <[email protected]>
@gshtras
[Bugfix] config.head_dim is now explicitly set to None (vllm-project#…
0c15c2e 
…18432)

Signed-off-by: Gregory Shtrasberg <[email protected]>
@bnellnm
[Bug] Fix moe_sum signature (vllm-project#18440)
92247c5 
Signed-off-by: Bill Nell <[email protected]>
@DarkLight1337
Revert "[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processin…
ad0012a 
…g Pure Text (vllm-project#18407)" (vllm-project#18456)

Signed-off-by: DarkLight1337 <[email protected]>
@wwl2755
[Bugfix][Failing Test] Fix nixl connector test when promt size < bloc…
d06dd72 
…k size (vllm-project#18429)

Signed-off-by: wwl2755 <[email protected]>
@NickLucche
[Misc] MultiConnector._connectors type (vllm-project#18423)
cd8dfc6 
Signed-off-by: nicklucche <[email protected]>
@kebe7jun
[Frontend] deprecate --device arg (vllm-project#18399)
5d7f545 
Signed-off-by: Kebe <[email protected]>
@sarckk
[V1] Fix general plugins not loaded in engine for multiproc (vllm-pro…
907f935 
…ject#18326)

Signed-off-by: Yong Hoon Shin <[email protected]>
@reidliu41
[Misc] refactor disaggregated-prefill-v1 example (vllm-project#18474)
107f5fc 
Signed-off-by: reidliu41 <[email protected]>
Co-authored-by: reidliu41 <[email protected]>
@rabi
[Bugfix][Failing Test] Fix test_events.py (vllm-project#18460)
61acfc4 
Signed-off-by: rabi <[email protected]>
@dhiaEddineRhaiem @younesbelkada
@ilyasch2 @JingweiZuo
[MODEL] FalconH1 (vllm-project#18406)
eca1869 
Signed-off-by: dhia.rhaiem <[email protected]>
Co-authored-by: younesbelkada <[email protected]>
Co-authored-by: Ilyas Chahed <[email protected]>
Co-authored-by: Jingwei Zuo <[email protected]>
vllmellm and others added 19 commits May 26, 2025 23:14
@vllmellm
[FEAT] [ROCm] Upgrade AITER Fused MoE kernels. (vllm-project#18271)
d260f79 
Signed-off-by: vllmellm <[email protected]>
@DarkLight1337
[Doc] Update OOT model docs (vllm-project#18742)
25a817f 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
[Doc] Update reproducibility doc and example (vllm-project#18741)
753944f 
Signed-off-by: DarkLight1337 <[email protected]>
@reidliu41
[Misc] improve docs (vllm-project#18734)
fc6d0c2 
Signed-off-by: reidliu41 <[email protected]>
Co-authored-by: reidliu41 <[email protected]>
@almersawi
feat(rocm-support): support mamba2 on rocm (vllm-project#18565)
a547aeb 
Signed-off-by: Islam Almersawi <[email protected]>
Co-authored-by: Islam Almersawi <[email protected]>
@ldurejko
[Hardware][Intel-Gaudi] [CI/Build] Fix multiple containers using the …
bbd9a84 
…same name in run-hpu-test.sh (vllm-project#18752)

Signed-off-by: Lukasz Durejko <[email protected]>
@calvin0327
[Doc] cleanup deprecated flag for doc (vllm-project#18715)
4693a34 
Signed-off-by: calvin chen <[email protected]>
@maobaolong
Minor fix about MooncakeStoreConnector (vllm-project#18721)
c24b157 
Signed-off-by: baoloongmao <[email protected]>
@kebe7jun
[Build] fix cpu build missing libtbbmalloc.so (vllm-project#18744)
e0f0ff8 
Signed-off-by: Kebe <[email protected]>
@huangyuxiang03
[BUG FIX] minicpm (vllm-project#18739)
6881107 
Signed-off-by: huangyuxiang03 <[email protected]>
Co-authored-by: huangyuxiang03 <[email protected]>
@Zerohertz
[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...)…
a68e293 
… to MkDocs format for better documentation linking (vllm-project#18663)

Signed-off-by: Zerohertz <[email protected]>
@DarkLight1337
[CI/Build] Remove imports of built-in re (vllm-project#18750)
4318c05 
Signed-off-by: DarkLight1337 <[email protected]>
@markmc
[V1][Metrics] Add API for accessing in-memory Prometheus metrics (vll…
06a0338 
…m-project#17010)

Signed-off-by: Mark McLoughlin <[email protected]>
@cascade812
Disable prefix cache by default for benchmark (vllm-project#18639)
aaa4ac1 
Signed-off-by: cascade812 <[email protected]>
@chunxiaozheng
optimize get_kv_cache_torch_dtype (vllm-project#18531)
6b6d496 
Signed-off-by: idellzheng <[email protected]>
@DarkLight1337
[Core] Automatically cast multi-modal input dtype (vllm-project#18756)
696259c 
Signed-off-by: DarkLight1337 <[email protected]>
@mgoin
[Bugfix] Mistral tool calling when content is list (vllm-project#18729)
5873877 
Signed-off-by: mgoin <[email protected]>
@gshtras
Merge remote-tracking branch 'upstream/main' into upstream_merge_2025…
1c450a5 
…_05_21
@gshtras
Merge remote-tracking branch 'origin/main' into upstream_merge_2025_0…
d5e35a9 
…5_21
@gshtras gshtras merged commit 1900335 into main May 27, 2025
2 of 5 checks passed
@gshtras gshtras deleted the upstream_merge_2025_05_27 branch May 27, 2025 16:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@shajrawi shajrawi shajrawi approved these changes

@Alexei-V-Ivanov-AMD Alexei-V-Ivanov-AMD Awaiting requested review from Alexei-V-Ivanov-AMD Alexei-V-Ivanov-AMD is a code owner

@maleksan85 maleksan85 Awaiting requested review from maleksan85 maleksan85 is a code owner

@sunway513 sunway513 Awaiting requested review from sunway513 sunway513 is a code owner

@hongxiayang hongxiayang Awaiting requested review from hongxiayang hongxiayang is a code owner

@divakar-amd divakar-amd Awaiting requested review from divakar-amd divakar-amd is a code owner

@charlifu charlifu Awaiting requested review from charlifu charlifu is a code owner

@mawong-amd mawong-amd Awaiting requested review from mawong-amd mawong-amd 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.