dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat(amdgpu): try to build in single binary (#2485)

Browse source 
* feat(amdgpu): try to build in single binary

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Release space from worker

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-05 08:44:15 +02:00 • committed by GitHub
parent fab3e711ff
commit 17cf6c4a4d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 92 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

20
pkg/model/initializers.go
View file

@ -37,6 +37,7 @@ const (
LLamaCPPAVX = "llama-cpp-avx"
LLamaCPPFallback = "llama-cpp-fallback"
LLamaCPPCUDA = "llama-cpp-cuda"
LLamaCPPHipblas = "llama-cpp-hipblas"
LLamaCPPGRPC = "llama-cpp-grpc"
Gpt4AllLlamaBackend = "gpt4all-llama"
@ -93,7 +94,7 @@ ENTRY:
if autoDetect {
// if we find the llama.cpp variants, show them of as a single backend (llama-cpp) as later we are going to pick that up
// when starting the service
foundLCPPAVX, foundLCPPAVX2, foundLCPPFallback, foundLCPPGRPC, foundLCPPCuda := false, false, false, false, false
foundLCPPAVX, foundLCPPAVX2, foundLCPPFallback, foundLCPPGRPC, foundLCPPCuda, foundLCPPHipblas := false, false, false, false, false, false
if _, ok := backends[LLamaCPP]; !ok {
for _, e := range entry {
if strings.Contains(e.Name(), LLamaCPPAVX2) && !foundLCPPAVX2 {
@ -116,6 +117,10 @@ ENTRY:
backends[LLamaCPP] = append(backends[LLamaCPP], LLamaCPPCUDA)
foundLCPPCuda = true
}
if strings.Contains(e.Name(), LLamaCPPHipblas) && !foundLCPPHipblas {
backends[LLamaCPP] = append(backends[LLamaCPP], LLamaCPPHipblas)
foundLCPPHipblas = true
}
}
}
}
@ -169,6 +174,7 @@ ENTRY:
// selectGRPCProcess selects the GRPC process to start based on system capabilities
func selectGRPCProcess(backend, assetDir string) string {
foundCUDA := false
foundAMDGPU := false
var grpcProcess string
// Select backend now just for llama.cpp
@ -195,10 +201,20 @@ func selectGRPCProcess(backend, assetDir string) string {
log.Info().Msgf("GPU device found but no CUDA backend present")
}
}
if strings.Contains(gpu.String(), "amd") {
p := backendPath(assetDir, LLamaCPPHipblas)
if _, err := os.Stat(p); err == nil {
log.Info().Msgf("[%s] attempting to load with HIPBLAS variant", backend)
grpcProcess = p
foundAMDGPU = true
} else {
log.Info().Msgf("GPU device found but no HIPBLAS backend present")
}
}
}
}
if foundCUDA {
if foundCUDA || foundAMDGPU {
return grpcProcess
}