Skip to content
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

Add deprecation notice to GPUSetting and split strategy #256

Merged
merged 1 commit into from
Mar 4, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions packages/lms-shared-types/src/llm/LLMLoadModelConfig.ts
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,8 @@ export const llmLlamaAccelerationOffloadRatioSchema = z.union([
* - "favorMainGpu": Fill the main GPU first, then fill the rest of the GPUs evenly
*
* @public
* @deprecated We are currently working on an improved way to control split. You can use this for
* now. We will offer the alternative before this feature is removed.
*/
export type LLMSplitStrategy = "evenly" | "favorMainGpu";
export const llmSplitStrategySchema = z.enum(["evenly", "favorMainGpu"]);
Expand All @@ -28,6 +30,8 @@ export const llmSplitStrategySchema = z.enum(["evenly", "favorMainGpu"]);
* Settings related to offloading work to the GPU.
*
* @public
* @deprecated We are currently working on an improved way to control split. You can use this for
* now. We will offer the alternative before this feature is removed.
*/
export type GPUSetting = {
/**
Expand Down Expand Up @@ -112,6 +116,8 @@ export interface LLMLoadModelConfig {
* How to distribute the work to your GPUs. See {@link GPUSetting} for more information.
*
* @public
* @deprecated We are currently working on an improved way to control split. You can use this for
* now but expect breakage in the future.
*/
gpu?: GPUSetting;

Expand Down