feat(llm): support local llm (lm_studio) #562
Open
+106
−7
Conversation
This file contains hidden or 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
The default context size (32768) for LM Studio was below the required RESERVED_TOKENS (50000), causing an AssertionError on startup. Changes: - Import RESERVED_TOKENS from kimisoul to stay in sync - Set default local context size to 131072 (128k) - Add minimum context size validation with user-friendly warning - Auto-correct values below minimum instead of failing
YoungY620
requested review from
Copilot and
stdrc
and removed request for
Copilot
YoungY620
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Outdated suggestions cannot be applied.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.
Related Issue
N/A
Description
Motivation
Add support for locally deployed models to enable more users to try Kimi CLI. LM Studio was chosen for its ease of use and broad accessibility.
(To be honest, I really need it. 🆘 I found no way but to change the code.)
Changes
New
lm_studioprovider (llm.py)Added dedicated provider for LM Studio. A separate provider was needed due to
httpxcompatibility issues (requires explicitAsyncHTTPTransportto work with LM Studio).LM Studio option in
/setup(setup.py)Added "LM Studio (Local)" to the setup wizard with auto-detection of loaded models.
Usage
Run
/setupand select "LM Studio (Local)", or configure manually: