GPTQ fixes #115
Closed
GPTQ fixes #115
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
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
HDCharles
added a commit
that referenced
this pull request
Apr 3, 2024
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: d29b6d73c90dec5171e12938afee25e5f42e042d Pull Request resolved: #115
facebook-github-bot
added
the
CLA Signed
|
@HDCharles - Changed the base to main in hope that CI will kick off |
cpuhrsch
reviewed
Apr 3, 2024
test/quantization/test_quant_api.py
Outdated
| def test_gptq_quantizer_gpt_fast(self): | ||
| from torchao.quantization.GPTQ import Int8DynActInt4WeightGPTQQuantizer, InputRecorder | ||
| # should be similar to TorchCompileDynamicQuantizer | ||
| precision = torch.bfloat16 | ||
| device = "cuda" | ||
| checkpoint_path = Path("../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth") | ||
| checkpoint_path = Path("/home/cdhernandez/local/gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth") |
There was a problem hiding this comment.
We definitely can't store this on CI. Maybe open_llama_7b works better. gpt-fast supports that as well.
HDCharles
added a commit
that referenced
this pull request
Apr 3, 2024
Summary: adding int4 gptq and eval support. Also fixed a few bugs relating to quantizing the activation both during gptq calculation and when calculating the output. Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: d29b6d73c90dec5171e12938afee25e5f42e042d Pull Request resolved: #115
Merged
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
HDCharles
added a commit
that referenced
this pull request
Apr 3, 2024
Summary: adding int4 gptq and eval support. Also fixed a few bugs relating to quantizing the activation both during gptq calculation and when calculating the output. Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 9d293f86255d16fb813c1d20a4c2e0dc5360e1cc Pull Request resolved: #115
HDCharles
added a commit
that referenced
this pull request
Apr 3, 2024
* add int4 gptq and eval Summary: adding int4 gptq and eval support. Also fixed a few bugs relating to quantizing the activation both during gptq calculation and when calculating the output. Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: d29b6d73c90dec5171e12938afee25e5f42e042d Pull Request resolved: #115 * add int4 gptq and eval Summary: adding int4 gptq and eval support. Also fixed a few bugs relating to quantizing the activation both during gptq calculation and when calculating the output. Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags: * remove debug from GPTQ Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags:
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
* add int4 gptq and eval Summary: adding int4 gptq and eval support. Also fixed a few bugs relating to quantizing the activation both during gptq calculation and when calculating the output. Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: d29b6d73c90dec5171e12938afee25e5f42e042d Pull Request resolved: pytorch#115 * add int4 gptq and eval Summary: adding int4 gptq and eval support. Also fixed a few bugs relating to quantizing the activation both during gptq calculation and when calculating the output. Test Plan: python test/quantization/test_quant_api.py Reviewers: Subscribers: Tasks: Tags: * remove debug from GPTQ Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags:
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
Update readme Update README.md (pytorch#113) update README.md Update README.md (pytorch#114) Update README.md (pytorch#115) Update Readme.md
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.
Stack from ghstack (oldest at bottom):
Summary:
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: