Extend remove_hooks to remove subsets
#1021
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Kyle Sayers <[email protected]>
|
👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review. |
Signed-off-by: Kyle Sayers <[email protected]>
kylesayrs
changed the title
remove_hooks to remove subsets
Signed-off-by: Kyle Sayers <[email protected]>
rahul-tuli
approved these changes
Jan 29, 2025
mgoin
approved these changes
Jan 29, 2025
dsikka
added a commit
that referenced
this pull request
Feb 5, 2025
## Purpose ##
* Allow subsets of handles to remain active, as is needed in the case of
wanda
```python3
def _get_activations(self, model, dataloader, nsamples=128):
def save_acts(module, input, name):
...
hooks = set(
self.register_hook(mod, partial(save_acts, name=name), "forward_pre")
for name, mod in self.model.named_modules()
if isinstance(mod, torch.nn.Linear) and "lm_head" not in name
)
# in the future, if the user puts wanda after another modifier,
# initialize will run after other modifiers have added hooks
# want to disable hooks from other modifiers, but keep the ones we just added
with HooksMixin.disable_hooks(keep=hooks):
run_basic(model, dataloader)
self.remove_hooks(hooks)
```
## Prerequisites ##
* #1021
## Postrequisites ##
* Layer compressor deprecation
## Changes ##
* Add a `_HOOKS_KEEP_ENABLED` class variable
## Tests ##
* Added `test_disable_hooks_keep` in tests
---------
Signed-off-by: Kyle Sayers <[email protected]>
Co-authored-by: Dipika Sikka <[email protected]>
dsikka
added a commit
that referenced
this pull request
Feb 5, 2025
## Purpose ## * Remove layer compressor to decouple modifiers from data pipelines * Reduce abstractions * Support VLMs with SparseGPT and Wanda ## Prerequisites ## * #1021 * #1023 * #1068 * #1030 ## Changes ## ### Interface/ Features ### * SparseGPT and Wanda now both support VLM architectures * Added `sequential_targets` to match GPTQ and made `targets` an alias * Support hessian offloading for `SparseGPT` * Add customized `_LinAlgError` for `SparseGPT` ### Implementations ### * Changed implementation styles of `SparseGPTModifier` and `WandaPruningModifier` to match `GPTQModifier` * Removed `LayerCompressor`, `ModuleCompressionWrapper`, `SparseGptWrapper`, and `WandaWrapper` * Shared implementations between SparseGPT and Wanda are implemented by the `SparsityModifierMixin` * Removed lines blocking `allow_tf32` * Maybe @rahul-tuli knows why this was originally implemented, potentially to avoid hardware issues? * This change was only present for wanda. Given that all other modifiers do not have this change, I see no reason why it should stay * Updated sparsegpt tests to reflect new implementation ### Tests ### * Updated obcq tests to reflect new implementations * Removed `test_sgpt_defaults.py` since this test doesn't test anything new or novel about this modifier ## Testing ## * `grep -r "LayerCompressor\|ModuleCompressionWrapper\|SparseGptWrapper\|WandaWrapper" src/ examples/ tests/` * Modified `test_invalid_layerwise_recipes_raise_exceptions` and `test_successful_layerwise_recipe` pass * `llama3_8b_2of4.py` passes and was evaluated with both SparseGPT and Wanda ## Potential Follow ups ## * Add module `targets` and `ignore` to SparseGPT and Wanda ## Regression Testing ## The hessian, row scalar, and compressed weight values were confirmed to be unchanged in the case that of one calibration sample. The final evaluations are different, which is likely due to numerical imprecision (dividing by int vs torch.int), different pipelines (different subgraph partitions => different imprecision from cpu offloading, potentially different module arguments). ### Evaluation Models were compressed using `examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py` <details><summary>sparsegpt</summary> Main ``` hf (pretrained=/home/ksayers/llm-compressor/old_Llama-3.2-1B-Instruct2of4-sparse,dtype=bfloat16,add_bos_token=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 1 | Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |----------|------:|------|-----:|------|---|-----:|---|-----:| |winogrande| 1|none | 5|acc |? |0.5391|? | 0.014| ``` Branch ``` hf (pretrained=/home/ksayers/llm-compressor/new_Llama-3.2-1B-Instruct2of4-sparse,dtype=bfloat16,add_bos_token=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 1 | Tasks |Version|Filter|n-shot|Metric| |Value| |Stderr| |----------|------:|------|-----:|------|---|----:|---|-----:| |winogrande| 1|none | 5|acc |? |0.547|? | 0.014| ``` </details> To test wanda, the `SparseGPTModifier` was replaced with the `WandaPruningModifier` <details><summary>wanda</summary> Main ``` hf (pretrained=/home/kyle/old_llm-compressor/Llama-3.2-1B-Instruct2of4-sparse,dtype=bfloat16,add_bos_token=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 1 | Tasks |Version|Filter|n-shot|Metric| |Value| |Stderr| |----------|------:|------|-----:|------|---|----:|---|-----:| |winogrande| 1|none | 5|acc |↑ |0.532|± | 0.014| ``` Branch ``` hf (pretrained=/home/kyle/llm-compressor/Llama-3.2-1B-Instruct2of4-sparse,dtype=bfloat16,add_bos_token=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 1 | Tasks |Version|Filter|n-shot|Metric| |Value | |Stderr| |----------|------:|------|-----:|------|---|-----:|---|-----:| |winogrande| 1|none | 5|acc |↑ |0.5414|± | 0.014| ``` </details> --------- Signed-off-by: Kyle Sayers <[email protected]> Co-authored-by: Dipika Sikka <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Purpose
Postrequisites
disable_hooksto keep subsets #1023Changes
_hooksfromListtoSethandlesargument toHooksMixin.remove_hooksTesting
test_remove_hooks_parameterizedtest