Support DeepSeek in benchmarks and plugin #56
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
GlebSolovev
requested changes
Jan 30, 2025
src/benchmark/framework/experiment/setupDSL/benchmarkingBundleBuilder.ts
Outdated
Show resolved
Hide resolved
GlebSolovev
approved these changes
Jan 31, 2025
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Outdated suggestions cannot be applied.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.
Implement DeepSeek API as a standalone service and support its choice in Benchmarks and Plugin settings. Due to API compatibility, the service is almost identical to the OpenAI Service. However, we decided to separate the logic into another service and not to manipulate existing service params because:
It is semantically a new LLMService.
The API is changing and could be extended. If we made it another way around, it would become painful to modify the code.
At the moment, service is not tested enough due to an outage of the public DeepSeek API, extreme downtime and queues.