chore: bump candle-nn from 0.8.4 to 0.11.0 - #5
Conversation
Bumps [candle-nn](https://github.com/huggingface/candle) from 0.8.4 to 0.11.0. - [Changelog](https://github.com/huggingface/candle/blob/main/CHANGELOG.md) - [Commits](huggingface/candle@0.8.4...0.11.0) --- updated-dependencies: - dependency-name: candle-nn dependency-version: 0.11.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com>
LabelsThe following labels could not be found: Please fix the above issues or remove invalid values from |
GitMind PR Review{'pr_url': '#5', 'repo': 'Ayyankhan101/Transformer-In-Rust', 'pr_num': '5', 'title': 'chore: bump candle-nn from 0.8.4 to 0.11.0', 'author': 'dependabot[bot]', 'additions': 283, 'deletions': 13, 'changed_files': 2, 'review': "## Summary\nThis PR updates the Auto-generated by GitMind — AI-powered code analysis. |
|
Superseded by #16, which takes this bump together with the other thirteen and verifies them against current master. All 10 CI checks pass there; the failures shown here were inherited from the pre-fix base commit, not caused by the bump. |
|
OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting If you change your mind, just re-open this PR and I'll resolve any conflicts on it. |
Bumps candle-nn from 0.8.4 to 0.11.0.
Commits
31f35b1Bump candle version to 0.11.0 (#3658)9bcfd98Add paged flash-attn kernels (#3655)c63cb20[CPU] Quantized perf improvements (#3643)5152ef6Support embedding forward pass for ggml quants (#3644)f53ed3bParameter cache for CUDA kernel launch (#3598)a9667caSupport cuda 13.3 (#3642)29a15c2Remove flash attn specific rayon threadpool. Use device.with_context around e...0190c65refactor: converge CPU flash attn kernels on shared primitives (#3513)c4b0faf[CPU] Persistent barrier based threadpool and improved qgemm (#3627)7625889[CPU] Add neon optimized path toBlockQ8K::from_float(#3629)Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting
@dependabot rebase.Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR:
@dependabot rebasewill rebase this PR@dependabot recreatewill recreate this PR, overwriting any edits that have been made to it@dependabot show <dependency name> ignore conditionswill show all of the ignore conditions of the specified dependency@dependabot ignore this major versionwill close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this minor versionwill close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this dependencywill close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)