Quantization Support #46
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
gavrissh
reviewed
Jan 3, 2024
| @@ -365,6 +369,8 @@ def execute(params: argparse.Namespace) -> None: | |||
| mount_path = params.mount_path | |||
| model_timeout = params.model_timeout | |||
|
|
|||
| quantize_bits = params.quantize_bits | |||
gavrissh
approved these changes
Jan 3, 2024
gavrissh
reviewed
Jan 4, 2024
llm/handler.py
Outdated
| @@ -112,8 +112,29 @@ def initialize(self, context: ts.context.Context): | |||
| self.tokenizer.padding_side = "left" | |||
| logger.info("Tokenizer loaded successfully") | |||
|
|
|||
| quantize_bits = self.get_env_value("NAI_QUANTIZATION") | |||
| quantize_bits = int(quantize_bits) if quantize_bits else quantize_bits | |||
There was a problem hiding this comment.
keep it simple here. you are doing the check, just to type cast
if self.get_env_value("NAI_QUANTIZATION"):
quantize_bits = int(self.get_env_value("NAI_QUANTIZATION"))
There was a problem hiding this comment.
changed as suggested
gavrissh
reviewed
Jan 4, 2024
llm/kubeflow_inference_run.py
Outdated
| @@ -382,6 +387,15 @@ def execute(params: argparse.Namespace) -> None: | |||
| model_info["repo_id"] = model_params["repo_id"] | |||
| model_info["repo_version"] = check_if_valid_version(model_info, mount_path) | |||
|
|
|||
| if quantize_bits and int(quantize_bits) not in [4, 8]: | |||
| print("## Quantization precision bits should be either 4 or 8") | |||
There was a problem hiding this comment.
There can be question, why it's not taking 16 as well. Add a text,
print("## Quantization precision bits should be either 4 or 8. Default precision used is 16")
There was a problem hiding this comment.
changed the mentioned message
gavrissh
approved these changes
Jan 4, 2024
gavrissh
approved these changes
Jan 5, 2024
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.
Changes: