added vllm lora support. #611
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
NathanHB
reviewed
Apr 8, 2025
| @ray.remote(num_gpus=1 if self.tensor_parallel_size == 1 else None) | ||
| def run_inference_one_model(model_args: dict, sampling_params: SamplingParams, requests): | ||
| llm = LLM(**model_args) | ||
| return llm.generate(prompt_token_ids=requests, sampling_params=sampling_params) | ||
| if self.lora_request is not None: | ||
| return llm.generate(prompt_token_ids=requests, sampling_params=sampling_params, lora_request=self.lora_request) |
There was a problem hiding this comment.
does passing lora_request=None results in a failure ? If not, we do not need the if statement
| sampling_params=sampling_params, | ||
| use_tqdm=True, | ||
| ) | ||
| if self.lora_request is not None: |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds the lora inference for the vllm backend, tested on single-node single-gpu (tensor-parallel and data-parallel themselves are broken).
Thanks!