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

Sync main with upstream #18

Merged
merged 19 commits into from
May 9, 2024
Merged

Sync main with upstream #18

merged 19 commits into from
May 9, 2024

Conversation

z103cb
Copy link

@z103cb z103cb commented May 9, 2024

Synchronizing main with upstream. Supersedes #15

Alexei-V-Ivanov-AMD and others added 5 commits May 8, 2024 11:12
@openshift-ci openshift-ci bot requested review from dtrifiro and vaibhavjainwiz May 9, 2024 09:41
@openshift-ci OpenShift CI
Copy link

openshift-ci bot commented May 9, 2024

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: z103cb

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

The pull request process is described 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

@openshift-ci openshift-ci bot added the approved label May 9, 2024
@z103cb z103cb mentioned this pull request May 9, 2024
Closed
rkooo567 and others added 14 commits May 9, 2024 12:42
@rkooo567 @z103cb
[Core] Optimize sampler get_logprobs (vllm-project#4594)
4ae5247
@rkooo567 @z103cb
[CI] Make mistral tests pass (vllm-project#4596)
6c53a43
@DefTruth @z103cb
[Bugfix][Kernel] allow non-power-of-2 for prefix prefill with alibi (v…
21d8850 
…llm-project#4573)
@WoosukKwon @z103cb
[Misc] Add get_name method to attention backends (vllm-project#4685)
bfef5df
@Yard1 @z103cb
[Core] Faster startup for LoRA enabled models (vllm-project#4634)
b74cdc3
@youkaichao @z103cb
[Core][Optimization] change python dict to pytorch tensor for blocks …
8f229ec 
…to swap (vllm-project#4659)
@youkaichao @z103cb
[CI/Test] fix swap test for multi gpu (vllm-project#4689)
cc3a658
@WoosukKwon @z103cb
[Misc] Use vllm-flash-attn instead of flash-attn (vllm-project#4686)
3ab3a02
@comaniac @cadedaniel @z103cb
[Dynamic Spec Decoding] Auto-disable by the running queue size (vllm-…
c08e3f1 
…project#4592)

Co-authored-by: Cade Daniel <[email protected]>
@cadedaniel @z103cb
[Speculative decoding] [Bugfix] Fix overallocation in ngram + spec lo…
3f6229f 
…gprobs (vllm-project#4672)
@alexm-neuralmagic @z103cb
[Bugfix] Fine-tune gptq_marlin configs to be more similar to marlin (v…
626f3f4 
…llm-project#4626)
@MahmoudAshraf97 @mgoin @z103cb
[Frontend] add tok/s speed metric to llm class when using tqdm (vllm-…
16fd703 
…project#4400)

Co-authored-by: Michael Goin <[email protected]>
@DarkLight1337 @z103cb
[Frontend] Move async logic outside of constructor (vllm-project#4674)
361c86f
@WoosukKwon @z103cb
[Misc] Remove unnecessary ModelRunner imports (vllm-project#4703)
f8de4ff
@openshift-ci OpenShift CI
Copy link

openshift-ci bot commented May 9, 2024 •
edited
Loading

@z103cb: The following test 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/pr-image-mirror a10b374a1fd3f172a0a115dc2e3eebb8a3fef372 link true /test pr-image-mirror

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.

@z103cb z103cb enabled auto-merge May 9, 2024 09:43
@dtrifiro
Copy link

dtrifiro commented May 9, 2024

/lgtm

@openshift-ci openshift-ci bot added the lgtm label May 9, 2024
@z103cb z103cb merged this pull request into opendatahub-io:main May 9, 2024
13 of 15 checks passed
@z103cb z103cb deleted the main_update branch May 9, 2024 10:38
@dtrifiro dtrifiro mentioned this pull request May 15, 2024
Merged
dtrifiro pushed a commit that referenced this pull request Jul 26, 2024
@joerunde
TGIS metrics (#18)
8c548e4 
This PR implements a subset of the metrics from the TGIS image. I tried
to make sure that everything from our current ops dashboard is
supported. These are:

- tgi_tokenize_request_tokens 
- tgi_tokenize_request_input_count 
- tgi_request_input_count 
- tgi_request_failure 
- tgi_request_queue_duration 
- tgi_queue_size 
- tgi_batch_current_size 
- tgi_batch_inference_duration 
- tgi_request_input_length 
- tgi_request_generated_tokens

---------

Signed-off-by: Joe Runde <[email protected]>
prarit pushed a commit to prarit/vllm that referenced this pull request Oct 18, 2024
@hongxiayang
Merge pull request opendatahub-io#18 from ROCm/dockerfile_install_mode
83ce7b2 
make the vllm setup mode configurable and make install mode as defaul…
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@dtrifiro dtrifiro Awaiting requested review from dtrifiro

@vaibhavjainwiz vaibhavjainwiz Awaiting requested review from vaibhavjainwiz

Assignees

@dtrifiro dtrifiro

Labels
approved lgtm
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.