Sourced from safetensors's releases.

v0.6.2

What's Changed

• Fixing clippy in 1.89 by @​Narsil in huggingface/safetensors#644
• Fixing the version check for uint support in torch. by @​Narsil in huggingface/safetensors#643

Full Changelog: huggingface/safetensors@v0.6.1...v0.6.2

v0.6.1

What's Changed

• Rust release upgrade (cache v1 is discontinued). by @​Narsil in huggingface/safetensors#627
• Re-adding support for u16, u32, u64. by @​Narsil in huggingface/safetensors#629
• Adding _safe_open_handle. by @​Narsil in huggingface/safetensors#608
• Fix test_simple.py for 0.6.0 by @​xanderlent in huggingface/safetensors#634
• GH action... once again. by @​Narsil in huggingface/safetensors#635
• Preparing for patch 6.0.1. by @​Narsil in huggingface/safetensors#638

New Contributors

• @​xanderlent made their first contribution in huggingface/safetensors#634

Full Changelog: huggingface/safetensors@v0.6.0...v0.6.1

v0.6.1-rc0

What's Changed

• Rust release upgrade (cache v1 is discontinued). by @​Narsil in huggingface/safetensors#627
• Re-adding support for u16, u32, u64. by @​Narsil in huggingface/safetensors#629
• Adding _safe_open_handle. by @​Narsil in huggingface/safetensors#608
• Fix test_simple.py for 0.6.0 by @​xanderlent in huggingface/safetensors#634
• GH action... once again. by @​Narsil in huggingface/safetensors#635
• Preparing for patch 6.0.1. by @​Narsil in huggingface/safetensors#638

New Contributors

• @​xanderlent made their first contribution in huggingface/safetensors#634

Full Changelog: huggingface/safetensors@v0.6.0...v0.6.1-rc0

v0.6.0

Biggest changes

• Added support for FP4/FP6 https://www.opencompute.org/documents/ocp-microscaling-formats-mx-v1-0-spec-final-pdf Support is still nascent in most frameworks (will require torch 2.8 which isn't released yet, and that will only support fp4 with caveats), however being an openspec supported by hardware manufacturers (and therefore hardware support most likely), it fits the bill of implementing it in safetensors (rather than all custom quantized formats existing in the wild in various frameworks.

  What FP4/FP6 mean, is that now a element of a tensor may have a non byte-aligned size/access. If you store a single fp4, then there is 4 bit on that byte that is outside of the spec. For now, safetensors library will simply raise MisalignedByte exception whenever an operation leads to unused/unaligned bits within a byte. Since most tensors are larger power of 2s, this shouldn't come up too often in practice. Raising an exception now means we have freedom later to actually implement a behavior which could align with tensor libraries.

  In that regard Dtype.size() is now deprecated, as it returns the size of the dtype in bytes, and we now favor bitsize() and it's up to users for now to handle something like len * bitsize() / 8 (and verifying the division is acceptable)

  On that note, and for Pytorch users specifically, torch doesn't actually implement fp4, it has a dtype called float4_e2m1fn_x2 which actually represents 2 fp4. This is why torch shouldn't have any alignement problems for now (but cannot implement fp6). But that also means that the shape of a [2, 2] tensor for floa4, contains actually 8 values. safetensors will actuallly silently cast a tensor of shape, [x, y, ...z] into [x, y, ..., z/2], using the last dimension to "swallow" , the x2 contained within the types. Again, there is no definite behavior just yet, so this might be subject to change.

What's Changed

• Add safestructures to Featured Projects by @​rachthree in huggingface/safetensors#570

... (truncated)

• aa6c43d Patch release 0.6.2
• 2b25340 Fixing the version check for uint support in torch. (#643)
• 5eecd29 Fixing clippy in 1.89 (#644)
• 94f5d38 Preparing for patch 6.0.1. (#638)
• b9ccdc6 GH action... once again. (#635)
• 7dfa63c Fix test_simple.py for 0.6.0 (#634)
• 48933f3 Adding _safe_open_handle. (#608)
• 8814598 Re-adding support for u16, u32, u64. (#629)
• 6544bf2 Rust release upgrade (cache v1 is discontinued). (#627)
• f79f19d Adding a failing test on the device cast. (#623)
• Additional commits viewable in compare view

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will 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 version will 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 dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)