What's Changed

• Back on dev. by @Narsil in https://github.com/huggingface/safetensors/pull/313
• Clarify specification around endianness and header padding by @akx in https://github.com/huggingface/safetensors/pull/306
• Adding new target for m1 by @Narsil in https://github.com/huggingface/safetensors/pull/317
• Fixing macos 13 release script (by prebuilding). by @Narsil in https://github.com/huggingface/safetensors/pull/315
• Cache dir all the time. by @Narsil in https://github.com/huggingface/safetensors/pull/319
• Supporting whisper conversion. by @Narsil in https://github.com/huggingface/safetensors/pull/320
• add tensorshare to featured projects by @chainyo in https://github.com/huggingface/safetensors/pull/322
• Fix Bench GH action. by @Narsil in https://github.com/huggingface/safetensors/pull/323
• Yaml is nice. by @Narsil in https://github.com/huggingface/safetensors/pull/325
• Fixing big endian. by @Narsil in https://github.com/huggingface/safetensors/pull/327
• Fixing boolean + numpy > 1.20 by @Narsil in https://github.com/huggingface/safetensors/pull/326
• Add NumPy for all backends dependencies by @chainyo in https://github.com/huggingface/safetensors/pull/332
• impl View for TensorView by @coreylowman in https://github.com/huggingface/safetensors/pull/329
• Reworked the release script entirely by @Narsil in https://github.com/huggingface/safetensors/pull/334
• Preparing small patch release (Big Endian fix). by @Narsil in https://github.com/huggingface/safetensors/pull/335
• Temporary revert of the breaking change (keep it for 0.4.0). by @Narsil in https://github.com/huggingface/safetensors/pull/336
• Don't release rust versions on RC by @Narsil in https://github.com/huggingface/safetensors/pull/337
• Fixing release script. by @Narsil in https://github.com/huggingface/safetensors/pull/338
• Python 3.8 for arm by @Narsil in https://github.com/huggingface/safetensors/pull/339
• Win64. by @Narsil in https://github.com/huggingface/safetensors/pull/342
• win64 by @Narsil in https://github.com/huggingface/safetensors/pull/343
• Trying out maturin. by @Narsil in https://github.com/huggingface/safetensors/pull/344
• Reduce memory allocations by @cospectrum in https://github.com/huggingface/safetensors/pull/350
• [docs] Convert weights by @stevhliu in https://github.com/huggingface/safetensors/pull/345
• Update types for load_model filename by @kevinhu in https://github.com/huggingface/safetensors/pull/356
• Fixing release script for windows aarch64 and 3.12 by @Narsil in https://github.com/huggingface/safetensors/pull/348
• Minor docstring edit to flax.py by @paulbricman in https://github.com/huggingface/safetensors/pull/359
• Stop recreating the hashmap all the time. by @Narsil in https://github.com/huggingface/safetensors/pull/363
• fix: add py.typed by @b-kamphorst in https://github.com/huggingface/safetensors/pull/365
• Preparing a new release (0.4.0). by @Narsil in https://github.com/huggingface/safetensors/pull/366
• Supporting bfloat16 for tensorflow + jax (was failing because of intermediary numpy). by @Narsil in https://github.com/huggingface/safetensors/pull/382
• Fix typo by @cccntu in https://github.com/huggingface/safetensors/pull/377
• Support fp8_e4m3/fp8_e5m2 by @Narsil in https://github.com/huggingface/safetensors/pull/383
• Better convert. by @Narsil in https://github.com/huggingface/safetensors/pull/384
• Ignore closed PRs to avoid spam. by @Narsil in https://github.com/huggingface/safetensors/pull/385
• Adding support for Ascend NPU by @statelesshz in https://github.com/huggingface/safetensors/pull/372
• Fix convert. by @Narsil in https://github.com/huggingface/safetensors/pull/390
• Upgrade dev version. by @Narsil in https://github.com/huggingface/safetensors/pull/392
• Fix/errors for some models including Mistral-7b and Flan-ul2 by @lachlancahill in https://github.com/huggingface/safetensors/pull/388
• Releasing for python 3.12/3.13 and testing on 3.11. by @Narsil in https://github.com/huggingface/safetensors/pull/393
• Adding stale action. by @Narsil in https://github.com/huggingface/safetensors/pull/398
• Document huggingface_hub.get_safetensors_metadata by @Wauplin in https://github.com/huggingface/safetensors/pull/417
• [docs] Update list of projects using safetensors by @mishig25 in https://github.com/huggingface/safetensors/pull/418
• Adding MLX backend. by @Narsil in https://github.com/huggingface/safetensors/pull/419
• [docs, untested] Attempt to fix links to source by @pcuenca in https://github.com/huggingface/safetensors/pull/420
• [docs] Use hfoptions for metadata by @mishig25 in https://github.com/huggingface/safetensors/pull/424
• Fix path in version_tag_suffix by @pcuenca in https://github.com/huggingface/safetensors/pull/426
• Removing old doc. by @Narsil in https://github.com/huggingface/safetensors/pull/427
• Fix missing Apache-2.0 license file in the published crate by @musicinmybrain in https://github.com/huggingface/safetensors/pull/416
• Implement PyTorch support for float8 types (F8_E5M2 and F8_E4M3) by @zeux in https://github.com/huggingface/safetensors/pull/404
• Fix mispelling of dictionary. by @hayden-donnelly in https://github.com/huggingface/safetensors/pull/410
• Add "xpu" device tag to the device list to support Intel GPU by @Narsil in https://github.com/huggingface/safetensors/pull/428
• Skip MLX bench for the bench runner. by @Narsil in https://github.com/huggingface/safetensors/pull/429

New Contributors

• @akx made their first contribution in https://github.com/huggingface/safetensors/pull/306
• @chainyo made their first contribution in https://github.com/huggingface/safetensors/pull/322
• @coreylowman made their first contribution in https://github.com/huggingface/safetensors/pull/329
• @cospectrum made their first contribution in https://github.com/huggingface/safetensors/pull/350
• @stevhliu made their first contribution in https://github.com/huggingface/safetensors/pull/345
• @kevinhu made their first contribution in https://github.com/huggingface/safetensors/pull/356
• @paulbricman made their first contribution in https://github.com/huggingface/safetensors/pull/359
• @b-kamphorst made their first contribution in https://github.com/huggingface/safetensors/pull/365
• @cccntu made their first contribution in https://github.com/huggingface/safetensors/pull/377
• @statelesshz made their first contribution in https://github.com/huggingface/safetensors/pull/372
• @lachlancahill made their first contribution in https://github.com/huggingface/safetensors/pull/388
• @Wauplin made their first contribution in https://github.com/huggingface/safetensors/pull/417
• @pcuenca made their first contribution in https://github.com/huggingface/safetensors/pull/420
• @musicinmybrain made their first contribution in https://github.com/huggingface/safetensors/pull/416
• @zeux made their first contribution in https://github.com/huggingface/safetensors/pull/404
• @hayden-donnelly made their first contribution in https://github.com/huggingface/safetensors/pull/410

Full Changelog: https://github.com/huggingface/safetensors/compare/v0.3.2...v0.4.2rc0