[Not for land] Util for saving quantized model #1280
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1280
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit ea41439 with merge base 9fb7999 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
reviewed
Oct 23, 2024
|
|
||
| from torchchat.utils.build_utils import set_precision | ||
|
|
||
| from torchao.quantization import quantize_, int8_weight_only |
There was a problem hiding this comment.
we now support tensor parallelism for int4_weight_only, float8_weight_only and float8_dynamic_activation_float8_weight as well I think, feel free to try out
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Outdated suggestions cannot be applied.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.
When composing distributed with quantization, one potential case is that the model has been quantized and saved so a second run do not need to quantize it again.
This is a script for quantizing a model and save it to disk.
The quantization can be done via either:
--quantize abc.json, orquantize_(model, int8_weight_only()).The latter is not in torchchat today.
Cc: @Jack-Khuu @jerryzh168