Release version v0.5.0 + add --hf-token, use hf-mem as lib, etc.#39
Draft
alvarobartt wants to merge 10 commits intomainfrom
Draft
Release version v0.5.0 + add --hf-token, use hf-mem as lib, etc.#39alvarobartt wants to merge 10 commits intomainfrom
version v0.5.0 + add --hf-token, use hf-mem as lib, etc.#39alvarobartt wants to merge 10 commits intomainfrom
Conversation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR sets the
versionto v0.5.0 by runninguv version 0.5.0prior the release; and also includeshf-memas a lib rather than only as a CLI, adds the--hf-tokenargument (closes #37, or at least makes it more explicit), and last but not least, uses Claude Sonnet 4.6 viapito refactor the codebase in an opinionated way (+ some manual intervention) due to the recent community contributions.Additionally, this PR moves out the KV cache estimation, and applies the feedback mentioned in https://huggingface.co/Qwen/Qwen3.5-397B-A17B/discussions/20#69a5bf82a2b3b0f27e8eacef to handle properly the full and sliding attention, rather than always assuming full attention + use the
head_dimif specified instead of calculating it; all the kudos here go to https://huggingface.co/YouJiacheng.CONTRIBUTING.md.