mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-22 14:53:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

image processing for llama3.2 (#6963)

Browse Source 
Co-authored-by: jmorganca <jmorganca@gmail.com>
Co-authored-by: Michael Yang <mxyng@pm.me>
Co-authored-by: Jesse Gross <jesse@ollama.com>
This commit is contained in:
Patrick Devine
2024-10-18 16:12:35 -07:00
committed by GitHub
parent bf4018b9ec
commit c7cb0f0602
35 changed files with 3851 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
llm/server.go
View File

@@ -442,26 +442,6 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
return nil, finalErr
}
func projectorMemoryRequirements(filename string) uint64 {
file, err := os.Open(filename)
if err != nil {
return 0
}
defer file.Close()
ggml, _, err := DecodeGGML(file, 0)
if err != nil {
return 0
}
var mem uint64
for _, layer := range ggml.Tensors().Layers() {
mem += layer.size()
}
return mem
}
type ServerStatus int
const ( // iota is reset to 0
@@ -673,8 +653,9 @@ ws ::= ([ \t\n] ws)?
const maxBufferSize = 512 * format.KiloByte
type ImageData struct {
Data []byte `json:"data"`
ID int `json:"id"`
Data []byte `json:"data"`
ID int `json:"id"`
AspectRatioID int `json:"aspect_ratio_id"`
}
type completion struct {