[lmi][lcnc] fallback to accelerate backend when non text-generation m… #1667
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
lanking520
reviewed
Mar 26, 2024
| @@ -46,6 +51,9 @@ public final class LmiConfigRecommender { | |||
| Map.entry("qwen2", "vllm"), | |||
| Map.entry("stablelm", "vllm")); | |||
|
|
|||
| private static final Set<String> OPTIMIZED_TASK_ARCHITECTURES = | |||
| Set.of("ForCausalLM", "LMHeadModel", "ForConditionalGeneration"); | |||
There was a problem hiding this comment.
https://huggingface.co/THUDM/chatglm3-6b/blob/main/config.json#L5 this is going to break
There was a problem hiding this comment.
ugh, that's good to know. didn't know about this type of config
There was a problem hiding this comment.
i've added auto_map to fix this use-case
lanking520
approved these changes
Mar 26, 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Outdated suggestions cannot be applied.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.
…odel is provided
Description
Fallback to accelerate for non text-generation model architectures.
From my limited testing, non text-generation architectures are not supported for rolling batch. For these models, we fall back to hf accelerate with dynamic batching.