NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #1992 most downloaded on PyPI
Library for utilization of compressed safetensors of neural network models
Latest stable
0.20.1
Last release 16 days ago
04 Nov 2026
Ships on a steady schedule
a new release about every 8 days
Most releases are documented
notes for 31 of 35 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
237 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Nothing published for this version
[Hotfix] Implement quantization compressor methods on dense compressor by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/344
force_cpu_offload by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/354offloaded_dispatch, implement disable_offloading by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/355register_offload_parameter by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/356offloaded_dispatch by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/357disable_offloading by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/360get_execution_device to support models by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/363get_execution_device by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/365Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.10.1...0.10.2
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
[Transform] Hadamard and Matrix Transform Utils by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/330
Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.10.0...0.10.1
Nothing published for this version
Nothing published for this version
Updates to build system by @dbarbuzzi in https://github.com/neuralmagic/compressed-tensors/pull/304
_initialize_scale_zero_point initializing on the wrong device by @mgoin in https://github.com/neuralmagic/compressed-tensors/pull/295match_param_name return type by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/312MSE by @shanjiaz in https://github.com/neuralmagic/compressed-tensors/pull/300RegistryMixin by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/320MSE (#300)" by @dsikka in https://github.com/neuralmagic/compressed-tensors/pull/323tensor_group strategy; enable NVFP4 Activations by @dsikka in https://github.com/neuralmagic/compressed-tensors/pull/317Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.9.4...0.10.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Remove compression_ratio calculation by @dsikka in https://github.com/neuralmagic/compressed-tensors/pull/293
Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.9.3...0.9.4
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
remove testmo by @dhuangnm in https://github.com/neuralmagic/compressed-tensors/pull/258
AttributeError in CompressedLinear by @rahul-tuli in https://github.com/neuralmagic/compressed-tensors/pull/273Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.9.2...0.9.3
ModelCompressor type checking import by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/220
COMPRESSION_PARAM_NAMES with Abstract Property by @rahul-tuli in https://github.com/neuralmagic/compressed-tensors/pull/249Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.9.1...0.9.2
BugFix: Shape should be a flat list by @rahul-tuli in https://github.com/neuralmagic/compressed-tensors/pull/241
Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.9.0...0.9.1
Replace depreciated pydantic functions by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/221
Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.8.1...0.9.0
Skip accelerate tests by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/208
Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.8.0...0.8.1
[Observer Restructure]: Separate out scale/zp and observer init; separate out calibration from forward pass by @dsikka in https://github.com/neuralmag
calibration, and applying frozen steps from lifecycle by @dsikka in https://github.com/neuralmagic/compressed-tensors/pull/189Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.7.1...0.8.0
[Observer Restructure]: Remove MemoryLess Observer; use helper function for dynamic quantization by @dsikka in https://github.com/neuralmagic/compress
Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.7.0...0.7.1
Make INT8 activation PRESET_SCHEMES explicit by @mgoin in https://github.com/neuralmagic/compressed-tensors/pull/158
compression_config to be quantization_config for HFQuantizer support by @dsikka in https://github.com/neuralmagic/compressed-tensors/pull/164apply_quantization_config misuse by @kylesayrs in https://github.com/neuralmagic/compressed-tensors/pull/180Full Changelog: https://github.com/neuralmagic/compressed-tensors/compare/0.6.0...0.7.0
Add simple GHA workflow to run tests by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/2
compressed-tensors by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/14compressed-tensors-nightly by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/53tests/quantization by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/99trust_remote_code=True by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/104compressed_tensors.utils by @rahul-tuli in https://github.com/neuralmagic/compressed-tensors/pull/102apply_quantization_config by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/107QuantizationScheme defaults by @dsikka in https://github.com/neuralmagic/compressed-tensors/pull/157Full Changelog: https://github.com/neuralmagic/compressed-tensors/commits/0.6.0
Add simple GHA workflow to run tests by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/2
compressed-tensors by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/14compressed-tensors-nightly by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/53tests/quantization by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/99trust_remote_code=True by @dbogunowicz in https://github.com/neuralmagic/compressed-tensors/pull/104compressed_tensors.utils by @rahul-tuli in https://github.com/neuralmagic/compressed-tensors/pull/102Full Changelog: https://github.com/neuralmagic/compressed-tensors/commits/0.5.0
Scheme alias support in quant config
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.