vllm
vllm copied to clipboard
[torch.compile] caching of config fields should be opt-out by default
Referring: https://github.com/vllm-project/vllm/issues/23107
Implements opt-out system of hashing, suggested by https://github.com/vllm-project/vllm/issues/16501
def compute_hash(self):
factors = list(self.__dict__.values())
factors.remove("enforce_eager")
factors.remove("tokenizer_config")
...
To-do's for followup:
- [ ] refactor configs to use compile_factors and return those instead of returning the hash. That way we can add the factors to the metadata as well.
- [ ] add the same system to the remaining configs
👋 Hi! Thank you for contributing to the vLLM project.
💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors.
You ask your reviewers to trigger select CI tests on top of fastcheck CI.
Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.
To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.
If you have any questions, please reach out to us on Slack at https://slack.vllm.ai.
🚀
This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @vnadathur.
https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork
This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @vnadathur.
https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork
This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @vnadathur.
https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork
This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @vnadathur.
https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork