dynquant-core
The pure-Python half of DynQuant: training-dynamics-driven mixed-precision LLM quantization.
Most users should pip install dynquant, which adds the prebuilt CUDA kernels.
Install dynquant-core directly when you want the quantization pipeline without
any binary dependency — CPU-only machines, Windows, macOS, ARM, and CI.
What is in here
dynquant.signals— the training-time hook and the stats file formatdynquant.graph— architecture-generic module role classificationdynquant.quant— group-wise n-bit packing and the quantizer driverdynquant.runtime— backend selection and the packedLineardynquant.cli— thedynquantcommand, includingdynquant doctor
Everything except inference speed works with no compiler and no GPU. The
reference (torch) backend dequantizes to compute, so it saves no memory and is
not fast — but it is the oracle the CUDA kernels are tested against, and it is
what makes quantizing a checkpoint possible on a laptop.
Install
pip install dynquant-core # quantize anywhere
pip install 'dynquant-core[hf]' # + transformers, accelerate
pip install 'dynquant-core[train]' # + peft, trl, datasets
pip install 'dynquant-core[dev]' # + pytest, ruff, mypy, docs
License
Apache-2.0.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file dynquant_core-0.5.0.tar.gz.
File metadata
- Download URL: dynquant_core-0.5.0.tar.gz
- Upload date:
- Size: 417.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
40c1ae26fa2b82533c564bcca429e79b8e7ef611b2b30964cbe06ac368348757
|
|
| MD5 |
52dc1f3a29a0fce65468a5c93e315a62
|
|
| BLAKE2b-256 |
acbd1b88fbb99badf124f3d244600ce15fad959b29dda16dd8c766c927f25dff
|
Provenance
The following attestation bundles were made for dynquant_core-0.5.0.tar.gz:
Publisher:
wheels.yml on kambojvikram/dynquant
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
dynquant_core-0.5.0.tar.gz -
Subject digest:
40c1ae26fa2b82533c564bcca429e79b8e7ef611b2b30964cbe06ac368348757 - Sigstore transparency entry: 2493845736
- Sigstore integration time:
-
Permalink:
kambojvikram/dynquant@6c21f00b269d0126e31fe6f9d9c02659c758c0e3 -
Branch / Tag:
refs/tags/v0.5.0 - Owner: https://github.com/kambojvikram
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
wheels.yml@6c21f00b269d0126e31fe6f9d9c02659c758c0e3 -
Trigger Event:
push
-
Statement type:
File details
Details for the file dynquant_core-0.5.0-py3-none-any.whl.
File metadata
- Download URL: dynquant_core-0.5.0-py3-none-any.whl
- Upload date:
- Size: 489.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4b9b76e6dae687f4b5fa54ab90c546ecb8c8f4ac69661d474ce8339444689cc3
|
|
| MD5 |
bc9b2ce8694e02794788201f772624fa
|
|
| BLAKE2b-256 |
9789df12f2366aa652742673060dd30f49e79a53621f4468732e2774fdc8ad37
|
Provenance
The following attestation bundles were made for dynquant_core-0.5.0-py3-none-any.whl:
Publisher:
wheels.yml on kambojvikram/dynquant
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
dynquant_core-0.5.0-py3-none-any.whl -
Subject digest:
4b9b76e6dae687f4b5fa54ab90c546ecb8c8f4ac69661d474ce8339444689cc3 - Sigstore transparency entry: 2493845857
- Sigstore integration time:
-
Permalink:
kambojvikram/dynquant@6c21f00b269d0126e31fe6f9d9c02659c758c0e3 -
Branch / Tag:
refs/tags/v0.5.0 - Owner: https://github.com/kambojvikram
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
wheels.yml@6c21f00b269d0126e31fe6f9d9c02659c758c0e3 -
Trigger Event:
push
-
Statement type:
