Skip to content

Rebase 06 06 #1383

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
Open
wants to merge 735 commits into
base: habana_main
Choose a base branch
from
Open

Rebase 06 06 #1383

wants to merge 735 commits into from

Conversation

michalkuligowski
Copy link

No description provided.

mgoin and others added 30 commits May 27, 2025 19:59
@mgoin
Support datasets in vllm bench serve and sync with benchmark_[servi…
e56f44d 
…ng,datasets].py (vllm-project#18566)
@cascade812
[Bugfix] Disable prefix caching by default for benchmark (vllm-projec…
51e98e4 
…t#18771)

Signed-off-by: cascade812 <cascade812@outlook.com>
@ProExpertProg
[Build] Fixes for CMake install (vllm-project#18570)
a3896c7
@lgeiger
[Core] Improve Tensor serialisation (vllm-project#18774)
d73a945 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
@fxmarty-amd
[rocm] Fix wrong attention log (vllm-project#18764)
794ae1f 
Signed-off-by: Felix Marty <felmarty@amd.com>
@noooop
[Bugfix] Fix nomic max_model_len (vllm-project#18755)
3e9ce60
@gcalmettes
[Bugfix]: correctly propagate errors message caught at the chat_templ…
9a21e33 
…ating step to the client (vllm-project#18769)

Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
@divakar-amd
[V1] fix torch profiling for V1 offline scenarios (vllm-project#18445)
774c5fd 
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
@RonaldBXu
[V1] [Bugfix] eagle bugfix and enable correct lm_head for multimodal …
5e13c07 
…(2) (vllm-project#18781)

Signed-off-by: Ronald Xu <ronaldxu@amazon.com>
@rabi
[Bugfix][FailingTest]Fix test_model_load_with_params.py (vllm-project…
b78f844 
…#18758)

Signed-off-by: rabi <ramishra@redhat.com>
@DarkLight1337
[Deprecation] Require overriding get_dummy_text and `get_dummy_mm_d…
7f2c1a8 
…ata` (vllm-project#18796)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
@DarkLight1337
[Deprecation] Remove unused sync methods in async_timeout (vllm-pro…
0f0926b 
…ject#18792)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
@DarkLight1337
[Deprecation] Remove fallbacks for Embeddings API (vllm-project#18795)
0c492b7 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
@noooop
[CI] improve embed testing (vllm-project#18747)
de65fc8
@zou3519
Fix PiecewiseCompileInterpreter (vllm-project#17338)
aa42561 
Signed-off-by: rzou <zou3519@gmail.com>
@LucasWilkinson
[BugFix] FA2 MLA Accuracy Issue (vllm-project#18807)
ce75efe 
Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>
@MengqingCao
[Platform][Dist] Make torch distributed process group extendable (vll…
d781930 
…m-project#18763)

Signed-off-by: Mengqing Cao <cmq0113@163.com>
@hmellor
Enable Pydantic mypy checks and convert configs to Pydantic dataclass…
4c2b38c 
…es (vllm-project#17599)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
@reidliu41
[Frontend] add run batch to CLI (vllm-project#18804)
435fa95 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
@daniel-salib
decrement server_load on listen for disconnect (vllm-project#18784)
6e4cea1 
Signed-off-by: Daniel Salib <danielsalib@meta.com>
@alex-jw-brooks
[Core] Add Lora Support to Beam Search (vllm-project#18346)
321331b 
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
@aarnphm
[Chore] update ty configuration (vllm-project#18839)
fced756 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
@lengrongfu
[Misc] fix olmoe model layer can't laod in tp gt 1 (vllm-project#18828)
c68b5c6 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
@markmc
[V1][Metrics] Remove metrics that were deprecated in 0.8 (vllm-projec…
0e98964 
…t#18837)

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
@aarnphm
[Chore][Spec Decode] Update check NoneType instead of assigning varia…
a09c7ca 
…bles (vllm-project#18836)

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
@Akshat-Tripathi @yaochengji
@xihajun @jdefreitas02
[Hardware][TPU][V1] Multi-LoRA Optimisations for the V1 TPU backend (v…
643622b 
…llm-project#15655)

Signed-off-by: Akshat Tripathi <akshat@krai.ai>
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Signed-off-by: xihajun <junfan@krai.ai>
Signed-off-by: Jorge de Freitas <jorge.de-freitas22@imperial.ac.uk>
Signed-off-by: Jorge de Freitas <jorge@krai.ai>
Co-authored-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: xihajun <junfan@krai.ai>
Co-authored-by: Jorge de Freitas <jorge.de-freitas22@imperial.ac.uk>
Co-authored-by: Jorge de Freitas <jorge@krai.ai>
@hmellor
Remove checks for None for fields which should never be None (vll…
6dbe5b5 
…m-project#17985)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
@varun-sundar-rabindranath
[Core] Enable CUDA graphs for DP + All2All kernels (vllm-project#18724)
7951d78 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
@hongxiayang @tjtanaa
[Bugfix][ROCm] fix the power of 2 exception from triton_unified_atten…
269d901 
…tion.py when running llama4 models and unit test fix (vllm-project#18100)

Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
@maxdebayser @DarkLight1337
Prevent the cross-encoder logic from being applied to classification …
515b413 
…tasks (vllm-project#18838)

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
@michalkuligowski
Copy link
Author

/run-gaudi-tests

@michalkuligowski
Copy link
Author

/run-gaudi-tests

@michalkuligowski
Copy link
Author

/run-gaudi-tests

@michalkuligowski
Copy link
Author

/run-gaudi-tests

@michalkuligowski
Copy link
Author

/run-gaudi-tests

@michalkuligowski
Copy link
Author

/run-gaudi-tests

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@kzawora-intel kzawora-intel Awaiting requested review from kzawora-intel kzawora-intel is a code owner

@madamczyk-intel madamczyk-intel Awaiting requested review from madamczyk-intel madamczyk-intel is a code owner

@mgawarkiewicz-intel mgawarkiewicz-intel Awaiting requested review from mgawarkiewicz-intel mgawarkiewicz-intel is a code owner

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

@afierka-intel afierka-intel Awaiting requested review from afierka-intel afierka-intel is a code owner

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

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

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

At least 1 approving review is required to merge this pull request.

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

Successfully merging this pull request may close these issues.