Add class that implements BaseCausalLMModel but is backed by an IREE module #393
+102
−1
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
…odule This is meant only for testing. It may not be performant as it marshals tensors and uses the IREE Python bindings.
|
This PR depends on #383. |
rsuderman
requested changes
Nov 6, 2024
| @@ -43,3 +53,106 @@ def make_llama_attention_block_theta( | |||
| ), | |||
| } | |||
| ) | |||
|
|
|||
|
|
|||
| class CausalLMIreeModel(BaseCausalLMModel, CausalLMModelABC): | |||
There was a problem hiding this comment.
Dependent on the double inheritance PR you have. This should have a cleaner design rather than extend with double inheritance.
There was a problem hiding this comment.
I removed CausalLMModelABC.
sogartar
changed the title
sogartar
changed the title
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Outdated suggestions cannot be applied.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.
The exported IREE LLM models have only prefill/decode that accept sequence lengths, so the default implementations in BaseCausalLMModel must be overridden.
This is meant only for testing. It may not be performant as it marshals tensors and uses the IREE Python bindings.