-
-
Notifications
You must be signed in to change notification settings - Fork 86
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Dynamic Generator #109
Merged
Merged
Dynamic Generator #109
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
Adds basic support for ExllamaV2's dynamic generator. Can generate a streaming and non-streaming completion. Signed-off-by: kingbri <[email protected]>
Dynamic gen takes in filters differently. Adjust to set the filter list per class rather than in the generation function. Signed-off-by: kingbri <[email protected]>
The new async dynamic job allows for native async support without the need of threading. Also add logprobs and metrics back to responses. Signed-off-by: kingbri <[email protected]>
Dynamic generator needed multiple prompts to be tokenized and sent for them to be sampled in serial, but generated in parallel. Signed-off-by: kingbri <[email protected]>
In the form of min_new_tokens. Stopping strings take priority. Signed-off-by: kingbri <[email protected]>
The dynamic generator requires Flash attention 2.5.7 or higher to be installed. This is only supported on Nvidia's 30 series and higher. If a card is AMD or lower than the 30 series, switch to compatability mode which functions the same way as the older generator, except without parallel batching and any features that depend on it, such as CFG. Signed-off-by: kingbri <[email protected]>
Add a sequential lock and wait until jobs are completed before executing any loading requests that directly alter the model. However, we also need to block any new requests that come in until the load is finished, so add a condition that triggers once the lock is free. Signed-off-by: kingbri <[email protected]>
v0.1.0 Signed-off-by: kingbri <[email protected]>
FA2 v2.5.7 and up is not supported below ampere and on AMD GPUs. Clarify the error message and explain what happens as a result. Signed-off-by: kingbri <[email protected]>
No need to use extend if the array is length 1. Signed-off-by: kingbri <[email protected]>
List comprehensions are the more "pythonic" way to approach mapping values to a list. They're also more flexible across different collection types rather than the inbuilt map method. It's best to keep one convention rather than splitting down two. Signed-off-by: kingbri <[email protected]>
This was referenced May 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.
Why should this feature be added?
Dependency compat upgrade
Additional context
Adds support for ExllamaV2's dynamic generator which handles prompt processing and multi-user management internally.
Resolves #77, #98, #107