Add KV cache quantization types #114
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
neilmehta24
force-pushed
the
ryan/add-kv-cache-quantization-options
branch
from
3486867 to
aa568e0
Compare
yagil
reviewed
Jan 15, 2025
| @@ -0,0 +1,14 @@ | |||
| import { z } from "zod"; | |||
|
|
|||
There was a problem hiding this comment.
since we'll (probably?) have MLX types here too, let's drop Llama from the file name. This is the pattern we use in LLMLoadModelConfig.ts. Btw, shouldn't it just live in that file?
There was a problem hiding this comment.
I deleted this file, but kept llama in the variable names since the MLX KV cache quantization implementation requires a different type.
yagil
reviewed
Jan 15, 2025
| LLMLlamaCacheQuantizationType, | ||
| llmLlamaCacheQuantizationTypes, | ||
| llmLlamaCacheQuantizationTypeSchema, | ||
| } from "./llm/LLMLlamaCacheQuantizationType"; |
There was a problem hiding this comment.
Suggested change
| } from "./llm/LLMLlamaCacheQuantizationType"; | |
| } from "./llm/LLMLlamaCacheQuantizationType.js"; |
but probably should move to LLMLoadModelConfig anyway
There was a problem hiding this comment.
I moved these to LLMLoadModelConfig
neilmehta24
force-pushed
the
ryan/add-kv-cache-quantization-options
branch
from
f9009cf to
6f1e8f5
Compare
neilmehta24
force-pushed
the
ryan/add-kv-cache-quantization-options
branch
from
6f1e8f5 to
13c4a57
Compare
yagil
approved these changes
Jan 15, 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Outdated suggestions cannot be applied.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.
Adds KV cache quantization configuration