[Bugfix] Only quant-compress modules with weight quantization #387
Conversation
This file contains hidden or 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 <kylesayrs@gmail.com>
kylesayrs
changed the title
shanjiaz
approved these changes
Jul 10, 2025
dsikka
approved these changes
Jul 11, 2025
kylesayrs
added a commit
to vllm-project/llm-compressor
that referenced
this pull request
Jul 11, 2025
…uantization (#1635) ## Purpose ## * Fix KV cache tests, whose models only have activation quantization ## Background Previously, `is_model_quantized` would only check for quantization on leaf modules. Now it checks on attention modules as well, but since we have examples of attention modules with only activation quantization, this triggers a bug in `infer_quantization_format` ## Testing ## * Requires neuralmagic/compressed-tensors#387 to pass KV cache tests --------- Signed-off-by: Kyle Sayers <kylesayrs@gmail.com> Co-authored-by: Dipika Sikka <dipikasikka1@gmail.com>
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Outdated suggestions cannot be applied.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
Changes
map_module_to_schemeused to only quantize compress leaf modules. Now, this method only quantize compresses modules with weight quantizationTesting
infer_quantization_formatwhen model only has activation quantization vllm-project/llm-compressor#1635