Skip to content
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

[do-not-merge] Ibm 20241211 #257

Open
wants to merge 329 commits into
base: main
Choose a base branch
from
Open

[do-not-merge] Ibm 20241211 #257

wants to merge 329 commits into from
+35,569 −13,878

Conversation

fialhocoelho
Copy link

Build image with fastsafetensors

alex-jw-brooks and others added 30 commits November 21, 2024 10:46
@alex-jw-brooks @DarkLight1337
[Model] Add Support for Multimodal Granite Models (vllm-project#10291)
1cfde82 
Signed-off-by: Alex-Brooks <[email protected]>
Co-authored-by: Cyrus Leung <[email protected]>
@sywangyi
fix the issue that len(tokenizer(prompt)["input_ids"]) > prompt_len (v…
8a93a59 
…llm-project#10524)

Signed-off-by: Wang, Yi A <[email protected]>
@Isotr0py
[Model] Expose dynamic_image_size as mm_processor_kwargs for Intern…
d5ec121 
…VL2 models (vllm-project#10518)

Signed-off-by: Isotr0py <[email protected]>
@BBuf
[Bugfix] Embedding model pooling_type equals ALL and multi input's bug (
4d676f0 
vllm-project#10494)
@chaunceyjiang
[Bug]: When apply continue_final_message for OpenAI server, the "echo…
da7e702 
…":false is ignored (vllm-project#10180)

Signed-off-by: chaunceyjiang <[email protected]>
@jeejeelee
[Kernel] Register punica ops directly (vllm-project#10522)
2385b60 
Signed-off-by: Jee Jee Li <[email protected]>
@ywang96
[Misc] Suppress duplicated logging regarding multimodal input pipeline (
c51e397 
vllm-project#10530)

Signed-off-by: Roger Wang <[email protected]>
@DarkLight1337
[Bugfix] Allow token ID-only inputs in Qwen2-Audio (vllm-project#10536)
e7a8341 
Signed-off-by: DarkLight1337 <[email protected]>
@youkaichao
[8/N] enable cli flag without a space (vllm-project#10529)
7560ae5 
Signed-off-by: youkaichao <[email protected]>
@WoosukKwon
[V1] Fix Compilation config & Enable CUDA graph by default (vllm-proj…
f9310cb 
…ect#10528)

Signed-off-by: Woosuk Kwon <[email protected]>
@cermeng @simon-mo
[CI][Installation] Avoid uploading CUDA 11.8 wheel (vllm-project#10535)
edec338 
Signed-off-by: simon-mo <[email protected]>
Co-authored-by: simon-mo <[email protected]>
@youkaichao
[misc] improve error message (vllm-project#10553)
cf656f5 
Signed-off-by: youkaichao <[email protected]>
@WoosukKwon
[Minor] Revert change in offline inference example (vllm-project#10545)
46fe9b4 
Signed-off-by: Woosuk Kwon <[email protected]>
@mgoin
Add small example to metrics.rst (vllm-project#10550)
9afa014
@simon-mo
[Benchmark] Add new H100 machine (vllm-project#10547)
aed0748
@youkaichao
[9/N] torch.compile LLM usage (vllm-project#10552)
33e0a25 
Signed-off-by: youkaichao <[email protected]>
@WoosukKwon
[Minor] Fix line-too-long (vllm-project#10563)
446c780 
Signed-off-by: Woosuk Kwon <[email protected]>
@youkaichao @njhill
[platforms] absorb worker cls difference into platforms folder (vllm-…
a111d01 
…project#10555)

Signed-off-by: youkaichao <[email protected]>
Co-authored-by: Nick Hill <[email protected]>
@Isotr0py
[Bugfix] Fix Phi-3 BNB quantization with tensor parallel (vllm-projec…
b6374e0 
…t#9948)

Signed-off-by: Isotr0py <[email protected]>
@noamgat
Remove token-adding chat embedding params (vllm-project#10551)
11fcf0e 
Signed-off-by: Noam Gat <[email protected]>
@youkaichao
[bugfix] fix full graph tests (vllm-project#10581)
db100c5 
Signed-off-by: youkaichao <[email protected]>
@youkaichao
[torch.compile] support all attention backends (vllm-project#10558)
eebad39 
Signed-off-by: youkaichao <[email protected]>
@rickyyx @comaniac
[v1] Refactor KVCacheManager for more hash input than token ids (vllm…
97814fb 
…-project#10507)

Signed-off-by: rickyx <[email protected]>
Signed-off-by: Cody Yu <[email protected]>
Co-authored-by: Cody Yu <[email protected]>
@zixuanzhang226
support bitsandbytes quantization with qwen model (vllm-project#10549)
948c859 
Signed-off-by: Ubuntu <[email protected]>
@russellb
[Core] remove temporary local variables in LLMEngine.__init__ (vllm-p…
28598f3 
…roject#10577)

Signed-off-by: Russell Bryant <[email protected]>
@Abatom
[V1] EngineCore supports profiling (vllm-project#10564)
d345f40 
Signed-off-by: Abatom <[email protected]>
@youkaichao
[bugfix] fix cpu tests (vllm-project#10585)
d559979 
Signed-off-by: youkaichao <[email protected]>
@tjohnson31415
[Bugfix][Frontend] Update Llama Chat Templates to also support Non-To…
9195dbd 
…ol use (vllm-project#10164)

Signed-off-by: Travis Johnson <[email protected]>
@russellb
[Core] Fix broken log configuration (vllm-project#10458)
ebda519 
Signed-off-by: Russell Bryant <[email protected]>
@tlrmchlsmth
[Misc] Add pynccl wrappers for all_gather and reduce_scatter (vllm-pr…
978b397 
…oject#9432)
youkaichao and others added 8 commits December 11, 2024 10:59
@youkaichao
[torch.compile] remove graph logging in ci (vllm-project#11110)
66aaa77 
Signed-off-by: youkaichao <[email protected]>
@ruisearch42
[core] Bump ray to use _overlap_gpu_communication in compiled graph t…
72ff3a9 
…ests (vllm-project#10410)

Signed-off-by: Rui Qiao <[email protected]>
Signed-off-by: Rui Qiao <[email protected]>
Co-authored-by: Rui Qiao <[email protected]>
@DarkLight1337
[CI/Build] Split up VLM tests (vllm-project#11083)
d1e21a9 
Signed-off-by: DarkLight1337 <[email protected]>
@tlrmchlsmth
[V1][Core] Remove should_shutdown to simplify core process termination (
452a723 
vllm-project#11113)

Signed-off-by: Tyler Michael Smith <[email protected]>
@fialhocoelho
Merge branch 'main' of https://github.com/vllm-project/vllm into ibm-…
742d0a4 
…20241211

Signed-off-by: Jefferson Fialho <[email protected]>
@fialhocoelho
Squash 6357
e22a57a 
Signed-off-by: Jefferson Fialho <[email protected]>
@fialhocoelho
Squash 10235
9c7773c 
Signed-off-by: Jefferson Fialho <[email protected]>
@fialhocoelho
Squash 10647
97a6423 
Signed-off-by: Jefferson Fialho <[email protected]>
@fialhocoelho fialhocoelho requested a review from njhill as a code owner December 12, 2024 13:40
@fialhocoelho fialhocoelho self-assigned this Dec 12, 2024
@openshift-ci OpenShift CI
Copy link

openshift-ci bot commented Dec 12, 2024

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: fialhocoelho
Once this PR has been reviewed and has the lgtm label, please assign xaenalt for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@fialhocoelho fialhocoelho force-pushed the ibm-20241211 branch 13 times, most recently from 11267fc to f56598f Compare December 13, 2024 17:24
@openshift-ci OpenShift CI
Copy link

openshift-ci bot commented Dec 13, 2024

@fialhocoelho: The following tests failed, say /retest to rerun all failed tests or /retest-required to rerun all mandatory failed tests:

Test name Commit Details Required Rerun command
ci/prow/smoke-test f56598f link true /test smoke-test
ci/prow/cuda-pr-image-mirror f56598f link true /test cuda-pr-image-mirror
ci/prow/images f56598f link true /test images

Full PR test history. Your PR dashboard.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here.

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

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

@RH-steve-grubb RH-steve-grubb Awaiting requested review from RH-steve-grubb

@vaibhavjainwiz vaibhavjainwiz Awaiting requested review from vaibhavjainwiz

Assignees

@fialhocoelho fialhocoelho

Labels
do-not-merge/hold
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.