sparseml
sparseml copied to clipboard
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
When running the imagenet training script from torchvision (i.e `src/sparseml/pytorch/image_classification/train.py`) I face the deadlock issue at certain random moment of training (in between the training epoch, usually somewhere in between...
This PR represents the dev branch for all `sparseml.recipe_template` related code; This PR is in draft mode and will be merged into main on feature completion, The PR has been...
Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 3.17.3 to 3.18.3. Release notes Sourced from protobuf's releases. Protocol Buffers v3.18.3 C++ Reduce memory consumption of MessageSet parsing This release addresses a Security Advisory for C++...
a core feature of the QuantizationModifier refactor is the ability for users to have both more simple and more fine grained control over how quantization is applied at large and...
This PR adds testing support for analyzer models and node shape for both torch 1.9 and 1.12. - Each has a data directory with both `torch-1.9` and `torch-1.12` directories. -...
first PR for QuantizationModifier refactor. moves the existing modifier and tests into a "legacy" file. Creates a template object for the new modifier. To maintain backwards compatibility, we add support...
This PR adds a `ModifierBuildInfo` class with state + utility methods for building a recipe from `modifier(s)` This also adds a registry for various pruning and quantization modifiers, that will...
This PR adds a CLI for `sparseml.recipe_template` + automated tests TODO: - [ ] Change base to `sparsify.recipe_template.dev` before landing
This PR adds getters for fetching `ModifierBuildInfo` objects from registry based off of args specified by user TODO: - [ ] Change base to `sparseml.recipe_template.dev` before landing
This feature improves OBSPruningModifier by allowing to recompute inverse Hessian `num_recomputations` times when doing a pruning step. For example, in the standard pipeline we would ask OBSPruningModifier to prune a...