Skip to content

Rebase apr 25#1166

Merged
michalkuligowski merged 409 commits intohabana_mainfrom
rebase_Apr_25
Apr 30, 2025
Merged

Rebase apr 25#1166
michalkuligowski merged 409 commits intohabana_mainfrom
rebase_Apr_25

Conversation

@michalkuligowski
Copy link
Copy Markdown

@michalkuligowski michalkuligowski commented Apr 25, 2025

No description provided.

taneem-ibrahim and others added 30 commits April 14, 2025 20:06
@taneem-ibrahim @mgoin
[BugFix]: Update minimum pyzmq version (vllm-project#16549)
70e7ed8 
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
@tlrmchlsmth
[Bugfix] Fix tests/kernels/test_mamba_ssm_ssd.py (vllm-project#16623)
dbb036c 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
@pooyadavoodi
[Bugfix] Fix broken GritLM model and tests (missing pooling_metadata) (…
bc5dd4f 
…vllm-project#16631)

Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
@mgoin
Add vllm bench [latency, throughput] CLI commands (vllm-project#16508)
b4fe16c 
Signed-off-by: mgoin <mgoin64@gmail.com>
@zou3519
Fix vLLM x torch.compile config caching (vllm-project#16491)
b590adf 
Signed-off-by: rzou <zou3519@gmail.com>
@reidliu41
[Misc] refactor argument parsing in examples (vllm-project#16635)
6ae996a 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
@jeejeelee
[CI/Build] Fix LoRA OOM (vllm-project#16624)
1575c17 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
@Cangxihui
Add "/server_info" endpoint in api_server to retrieve the vllm_config…
1666e66 
….  (vllm-project#16572)

Signed-off-by: Xihui Cang <xihuicang@gmail.com>
@DefTruth
[Kernel] Remove redundant Exp calculations (vllm-project#16123)
280d62b 
Signed-off-by: DefTruth <qiustudent_r@163.com>
@dsikka
[Misc] Update compressed-tensors WNA16 to support zero-points (vllm…
54a66e5 
…-project#14211)
@angkywilliam
[Misc] Enable vLLM to Dynamically Load LoRA from a Remote Server (vll…
fdcb850 
…m-project#10546)

Signed-off-by: Angky William <angkywilliam@Angkys-MacBook-Pro.local>
Co-authored-by: Angky William <angkywilliam@Angkys-MacBook-Pro.local>
@Alnusjaponica @nzw0301
@HiroakiMikami @nopperl
[Model] Add PLaMo2 (vllm-project#14323)
3badb02 
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
Signed-off-by: shemmi <shemmi@preferred.jp>
Co-authored-by: Kento Nozawa <nzw0301@preferred.jp>
Co-authored-by: Hiroaki Mikami <mhiroaki@preferred.jp>
Co-authored-by: Calvin Metzger <metzger@preferred.jp>
@lengrongfu
[Bugfix] fix gpu docker image mis benchmarks dir (vllm-project#16628)
96bb8aa 
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
@jeejeelee
[Misc] Modify LRUCache touch (vllm-project#16689)
0d7d05f 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
@zou3519
Disable remote caching when calling compile_fx (vllm-project#16611)
966c742 
Signed-off-by: rzou <zou3519@gmail.com>
@billishyahao
[Feature] add model aware kv ops helper (vllm-project#16020)
3ac98ed 
Signed-off-by: billishyahao <bill.he@amd.com>
@SageMoore
[ROCM] Bind triton version to 3.2 in requirements-built.txt (vllm-pro…
44fa4d5 
…ject#16664)

Signed-off-by: Sage Moore <sage@neuralmagic.com>
@shen-shanshan
[V1][Structured Output] Move xgrammar related utils to `backend_xgram…
976711d 
…mar.py` (vllm-project#16578)

Signed-off-by: shen-shanshan <467638484@qq.com>
@yankay
[CI] Cleanup additional_dependencies: [toml] for pre-commit yapf ho…
21378a2 
…ok (vllm-project#16405)

Signed-off-by: Kay Yan <kay.yan@daocloud.io>
@reidliu41
[Misc] refactor examples series (vllm-project#16708)
7168920 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
@DarkLight1337
[Doc] Improve OOM troubleshooting (vllm-project#16704)
facbe2a 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
@DefTruth
[Bugfix][Kernel] fix potential cuda graph broken for merge_attn_state…
e82ee40 
…s kernel (vllm-project#16693)

Signed-off-by: DefTruth <qiustudent_r@163.com>
@xsank
[Model] support modernbert (vllm-project#16648)
ee378f3 
Signed-off-by: 唯勤 <xsank.mz@alibaba-inc.com>
Co-authored-by: 唯勤 <xsank.mz@alibaba-inc.com>
@joerunde
[Hardware] Add processor inputs to platform validation (vllm-project#…
e1b0048 
…16680)

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
@hmellor
Improve error for structured output backend selection (vllm-project#1…
93e561e 
…6717)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
@jianzs
[Misc] Remove redundant comment (vllm-project#16703)
8a7368e 
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
@hmellor
Help user create custom model for Transformers backend remote code mo…
3cd91dc 
…dels (vllm-project#16719)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
@p88h @DarkLight1337 @njhill
[V1][Performance] Implement custom serializaton for MultiModalKwargs …
3092375 
…[Rebased] (vllm-project#16432)

Signed-off-by: Staszek Pasko <staszek@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
@luyuzhe111
[V1][Spec Dec Bug Fix] Respect Spec Dec Method Specification (vllm-pr…
2cbd4d2 
…oject#16636)

Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
@AaruniAggarwal
Adding vllm buildkite job for IBM Power (vllm-project#16679)
3c776dc 
Signed-off-by: Aaruni Aggarwal <aaruniagg@gmail.com>
@michalkuligowski
Copy link
Copy Markdown
Author

michalkuligowski commented Apr 29, 2025

/run-gaudi-tests

@michalkuligowski
Copy link
Copy Markdown
Author

michalkuligowski commented Apr 29, 2025

/run-gaudi-tests

@michalkuligowski
Copy link
Copy Markdown
Author

michalkuligowski commented Apr 30, 2025

/run-gaudi-tests

@michalkuligowski
Copy link
Copy Markdown
Author

michalkuligowski commented Apr 30, 2025

/run-gaudi-tests

@michalkuligowski
Update test_config.yaml
c7fe205 
Skipping mlp spec decode - failing with input_ = None
@michalkuligowski
Copy link
Copy Markdown
Author

michalkuligowski commented Apr 30, 2025

/run-gaudi-tests

@michalkuligowski
Copy link
Copy Markdown
Author

michalkuligowski commented Apr 30, 2025

/run-gaudi-tests

xuechendi
xuechendi approved these changes Apr 30, 2025
View reviewed changes
Copy link
Copy Markdown

@xuechendi xuechendi left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

approved

@michalkuligowski michalkuligowski merged commit d6f76ee into habana_main Apr 30, 2025
40 checks passed
@michalkuligowski michalkuligowski deleted the rebase_Apr_25 branch April 30, 2025 17:51
@zhouyu5 zhouyu5 mentioned this pull request May 15, 2025
Merged
jikunshang pushed a commit that referenced this pull request May 15, 2025
fix text only input for llama3.2 (#1262)
f57c119 
After PR #1166 , when give text-only input to llama3.2, the error will
occur,
`ValueError: The encoder prompt cannot be empty`

This PR fix this minor error.

Signed-off-by: zhouyu5 <yu.zhou@intel.com>
@michalkuligowski michalkuligowski restored the rebase_Apr_25 branch June 10, 2025 05:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@xuechendi xuechendi xuechendi approved these changes

@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

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

@jikunshang jikunshang Awaiting requested review from jikunshang jikunshang 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.