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

Skipping refactor #234

Closed
wants to merge 123 commits into from
Closed

Skipping refactor #234

wants to merge 123 commits into from

Conversation

robertgshaw2-neuralmagic
Copy link
Collaborator

@robertgshaw2-neuralmagic robertgshaw2-neuralmagic commented May 13, 2024 •
edited

To be merged after upstream sync

This PR does two things:

  • a) changes the set of tests that we run on remote push
  • b) converts to using environment variables to control the tests that are skipped, allowing us to track it in TestMo

njhill and others added 30 commits May 5, 2024 20:14
@njhill @robertgshaw2-neuralmagic
[Core] Add shutdown() method to ExecutorBase (vllm-project#4349)
7b11874
@njhill @robertgshaw2-neuralmagic
[Core] Move function tracing setup to util function (vllm-project#4352)
28590fc
@hongxiayang @WoosukKwon @robertgshaw2-neuralmagic
[ROCm][Hardware][AMD][Doc] Documentation update for ROCm (vllm-projec…
7873343 
…t#4376)

Co-authored-by: WoosukKwon <woosuk.kwon@berkeley.edu>
@DarkLight1337 @robertgshaw2-neuralmagic
[Bugfix] Fix parameter name in get_tokenizer (vllm-project#4107)
5f32d89
@normster @robertgshaw2-neuralmagic
[Frontend] Add --log-level option to api server (vllm-project#4377)
c20ff92
@rkooo567 @robertgshaw2-neuralmagic
[CI] Disable non-lazy string operation on logging (vllm-project#4326)
ec4050a 
Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>
@rkooo567 @robertgshaw2-neuralmagic
[Core] Refactoring sampler and support prompt logprob for chunked pre…
ee654c9 
…fill (vllm-project#4309)
@comaniac @robertgshaw2-neuralmagic
[Misc][Refactor] Generalize linear_method to be quant_method (vllm-pr…
4f5d020 
…oject#4373)
@youkaichao @simon-mo @robertgshaw2-neuralmagic
[Misc] add RFC issue template (vllm-project#4401)
dc47676 
Co-authored-by: Simon Mo <simon.mo@hey.com>
@njhill @robertgshaw2-neuralmagic
[Core] Introduce DistributedGPUExecutor abstract class (vllm-projec…
192c704 
…t#4348)
@pcmoritz @WoosukKwon @robertgshaw2-neuralmagic
[Kernel] Optimize FP8 support for MoE kernel / Mixtral via static sca…
1e88172 
…les (vllm-project#4343)

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
@DarkLight1337 @robertgshaw2-neuralmagic
[Frontend][Bugfix] Disallow extra fields in OpenAI API (vllm-project#…
b9e05fa 
…4355)
@esmeetu @robertgshaw2-neuralmagic
[Misc] Fix logger format typo (vllm-project#4396)
5395fa3
@hongxiayang @robertgshaw2-neuralmagic
[ROCm][Hardware][AMD] Enable group query attention for triton FA (vll…
cc7a791 
…m-project#4406)
@FurtherAI @Yard1 @robertgshaw2-neuralmagic
[Kernel] Full Tensor Parallelism for LoRA Layers (vllm-project#3524)
77c1eb1 
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
@caiom @robertgshaw2-neuralmagic
[Model] Phi-3 4k sliding window temp. fix (vllm-project#4380)
287d987
@esmeetu @robertgshaw2-neuralmagic
[Bugfix][Core] Fix get decoding config from ray (vllm-project#4335)
b3759af
@chestnut-Q @robertgshaw2-neuralmagic
[Bugfix] Abort requests when the connection to /v1/completions is int…
6a44e8e 
…errupted (vllm-project#4363)
@njhill @DefTruth @robertgshaw2-neuralmagic
[BugFix] Fix min_tokens when eos_token_id is None (vllm-project#4389
821a91a 
)

Co-authored-by: DefTruth <31974251+deftruth@users.noreply.github.com>
@prashantgupta24 @tjohnson31415 @robertgshaw2-neuralmagic
[Core] Support offline use of local cache for models (vllm-project#4374)
5a4c41b 
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Travis Johnson <tjohnson31415@gmail.com>
@njhill @robertgshaw2-neuralmagic
[BugFix] Fix return type of executor execute_model methods (vllm-proj…
593db14 
…ect#4402)
@robertgshaw2-neuralmagic
[BugFix] Resolved Issues For LinearMethod --> QuantConfig (vllm-proje…
1f87fe1 
…ct#4418)
@DefTruth @robertgshaw2-neuralmagic
[Misc] fix typo in llm_engine init logging (vllm-project#4428)
b24aae6
@ronensc @robertgshaw2-neuralmagic
Add more Prometheus metrics (vllm-project#2764)
6a8a97b 
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
@simon-mo @robertgshaw2-neuralmagic
[CI] clean docker cache for neuron (vllm-project#4441)
8ab0de8
@rkooo567 @robertgshaw2-neuralmagic
[mypy][5/N] Support all typing on model executor (vllm-project#4427)
7f5a450
@robertgshaw2-neuralmagic @alexm-neuralmagic @mgoin
[Kernel] Marlin Expansion: Support AutoGPTQ Models with Marlin (vllm-…
1e75df8 
…project#3922)

Co-authored-by: alexm <alexm@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
@simon-mo @robertgshaw2-neuralmagic
[CI] hotfix: soft fail neuron test (vllm-project#4458)
19187df
@youkaichao @robertgshaw2-neuralmagic
[Core][Distributed] use cpu group to broadcast metadata in cpu (vllm-…
43add77 
…project#4444)
@mgoin @robertgshaw2-neuralmagic
[Misc] Upgrade to torch==2.3.0 (vllm-project#4454)
768facf
@robertgshaw2-neuralmagic robertgshaw2-neuralmagic marked this pull request as ready for review May 13, 2024 00:26
@robertgshaw2-neuralmagic robertgshaw2-neuralmagic deleted the skipping-refactor branch June 9, 2024 23:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet