Hybrid Engine Refactor and Llama Inference Support #3425
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
* Refactor changes out of base container * Re-add to OPT * Align HE API * Break down release into components and add to feature containers * Consolidate copy methods * Align policy API * Missed file * Add missing arguments to qkv_gemm call * Aligning attributes, data types * Handle TP scaling * Python interface alignment, TP>1 now working * HybridEngineContainer, refactor changes out of Policy
cmikeh2
requested review from
jeffra,
tjruwase,
RezaYazdaniAminabadi,
mrwyattii,
awan-10 and
arashb
as code owners
…pSpeed into cholmes/llama-inference-v2
awan-10
reviewed
May 2, 2023
| @@ -29,6 +29,32 @@ def create_module(self, config=None): | |||
| self.module.config.scale_attention = self.scale_attention | |||
| return self.module | |||
|
|
|||
| def set_lora_params(self): | |||
| """ | |||
| Necessry to implement for `HybridEngineContainer` | |||
awan-10
approved these changes
May 2, 2023
lekurile
approved these changes
May 2, 2023
…pSpeed into cholmes/llama-inference-v2
loadams
approved these changes
May 3, 2023
…pSpeed into cholmes/llama-inference-v2
lekurile
added a commit
that referenced
this pull request
May 23, 2023
This PR fixes Hybrid Engine (HE) support for the BLOOM model, which was accidentally broken during the HE refactor in GH-3425. The BLOOM container now inherits the HybridEngineContainer feature and defines a set_lora_params() function necessary for the feature to work. get_lora_params() is correspondingly removed from the BLOOM policy class as well. GPT-NeoX was also cleaned up by removing a get_lora_params() function from its policy due to it no longer being used.
molly-smith
pushed a commit
that referenced
this pull request
Jun 23, 2023
This PR fixes Hybrid Engine (HE) support for the BLOOM model, which was accidentally broken during the HE refactor in GH-3425. The BLOOM container now inherits the HybridEngineContainer feature and defines a set_lora_params() function necessary for the feature to work. get_lora_params() is correspondingly removed from the BLOOM policy class as well. GPT-NeoX was also cleaned up by removing a get_lora_params() function from its policy due to it no longer being used.
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.
This PR introduces a number of features and bugfixes:
HybridEngineContaineritself or something more specialized for the particular model architecture.