upstream-archive/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-23 09:10:53 -05:00
Code Issues Packages Projects Releases Wiki Activity

launch: use vram bytes for model recommendations (#15885)

Browse Source
This commit is contained in:
Parth Sareen
2026-04-29 18:40:14 -07:00
committed by GitHub
parent bad32c7244
commit b6447caebc
6 changed files with 36 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
api/types.go
View File

@@ -813,7 +813,7 @@ type ModelRecommendation struct {
Description string `json:"description"`
ContextLength int `json:"context_length,omitempty"`
MaxOutputTokens int `json:"max_output_tokens,omitempty"`
VRAM string `json:"vram,omitempty"`
VRAMBytes int64 `json:"vram_bytes,omitempty"`
}
// ProcessResponse is the response from [Client.Process].