highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 11:37:23 +01:00
Code Issues Packages Projects Releases Wiki Activity

Revamp ROCm support

Browse Source 
This refines where we extract the LLM libraries to by adding a new
OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already
idempotenent, so this should speed up startups after the first time a
new release is deployed.  It also cleans up after itself.

We now build only a single ROCm version (latest major) on both windows
and linux.  Given the large size of ROCms tensor files, we split the
dependency out.  It's bundled into the installer on windows, and a
separate download on windows.  The linux install script is now smart and
detects the presence of AMD GPUs and looks to see if rocm v6 is already
present, and if not, then downloads our dependency tar file.

For Linux discovery, we now use sysfs and check each GPU against what
ROCm supports so we can degrade to CPU gracefully instead of having
llama.cpp+rocm assert/crash on us.  For Windows, we now use go's windows
dynamic library loading logic to access the amdhip64.dll APIs to query
the GPU information.
This commit is contained in:
Daniel Hiltgen
2024-02-15 17:15:09 -08:00
parent 2e20110e50
commit 6c5ccb11f9
27 changed files with 1091 additions and 588 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
server/routes.go
View File

@@ -66,8 +66,6 @@ var defaultSessionDuration = 5 * time.Minute
// load a model into memory if it is not already loaded, it is up to the caller to lock loaded.mu before calling this function
func load(c *gin.Context, model *Model, opts api.Options, sessionDuration time.Duration) error {
workDir := c.GetString("workDir")
needLoad := loaded.runner == nil || // is there a model loaded?
loaded.ModelPath != model.ModelPath || // has the base model changed?
!reflect.DeepEqual(loaded.AdapterPaths, model.AdapterPaths) || // have the adapters changed?
@@ -82,7 +80,7 @@ func load(c *gin.Context, model *Model, opts api.Options, sessionDuration time.D
loaded.Options = nil
}
llmRunner, err := llm.New(workDir, model.ModelPath, model.AdapterPaths, model.ProjectorPaths, opts)
llmRunner, err := llm.New(model.ModelPath, model.AdapterPaths, model.ProjectorPaths, opts)
if err != nil {
// some older models are not compatible with newer versions of llama.cpp
// show a generalized compatibility error until there is a better way to
@@ -1035,7 +1033,7 @@ func Serve(ln net.Listener) error {
os.Exit(0)
}()
if err := llm.Init(s.WorkDir); err != nil {
if err := llm.Init(); err != nil {
return fmt.Errorf("unable to initialize llm library %w", err)
}
if runtime.GOOS == "linux" { // TODO - windows too