Skip to content

Commit

Permalink
Merge pull request #256 from lmstudio-ai/ryan/deprecate-gpu
Browse files Browse the repository at this point in the history
Add deprecation notice to GPUSetting and split strategy
  • Loading branch information
yagil authored Mar 4, 2025
2 parents d760fae + 8514ac8 commit 6663b21
Showing 1 changed file with 6 additions and 0 deletions.
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

0 comments on commit 6663b21

Please sign in to comment.