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

Bump vLLM version + more options when loading models in vLLM (#1782)

Browse source 
* Bump vLLM version to 0.3.2

* Add vLLM model loading options

* Remove transformers-exllama

* Fix install exllama
This commit is contained in:
Ludovic Leroux 2024-03-01 16:48:53 -05:00 • committed by GitHub
parent 1c312685aa
commit 939411300a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 736 additions and 641 deletions
Download patch file Download diff file Expand all files Collapse all files

69
core/backend/options.go
View file

@ -40,38 +40,43 @@ func gRPCModelOpts(c config.BackendConfig) *pb.ModelOptions {
}
return &pb.ModelOptions{
ContextSize: int32(c.ContextSize),
Seed: int32(c.Seed),
NBatch: int32(b),
NoMulMatQ: c.NoMulMatQ,
CUDA: c.CUDA, // diffusers, transformers
DraftModel: c.DraftModel,
AudioPath: c.VallE.AudioPath,
Quantization: c.Quantization,
MMProj: c.MMProj,
YarnExtFactor: c.YarnExtFactor,
YarnAttnFactor: c.YarnAttnFactor,
YarnBetaFast: c.YarnBetaFast,
YarnBetaSlow: c.YarnBetaSlow,
LoraAdapter: c.LoraAdapter,
LoraBase: c.LoraBase,
LoraScale: c.LoraScale,
NGQA: c.NGQA,
RMSNormEps: c.RMSNormEps,
F16Memory: c.F16,
MLock: c.MMlock,
RopeFreqBase: c.RopeFreqBase,
RopeScaling: c.RopeScaling,
Type: c.ModelType,
RopeFreqScale: c.RopeFreqScale,
NUMA: c.NUMA,
Embeddings: c.Embeddings,
LowVRAM: c.LowVRAM,
NGPULayers: int32(c.NGPULayers),
MMap: c.MMap,
MainGPU: c.MainGPU,
Threads: int32(c.Threads),
TensorSplit: c.TensorSplit,
ContextSize: int32(c.ContextSize),
Seed: int32(c.Seed),
NBatch: int32(b),
NoMulMatQ: c.NoMulMatQ,
CUDA: c.CUDA, // diffusers, transformers
DraftModel: c.DraftModel,
AudioPath: c.VallE.AudioPath,
Quantization: c.Quantization,
GPUMemoryUtilization: c.GPUMemoryUtilization,
TrustRemoteCode: c.TrustRemoteCode,
EnforceEager: c.EnforceEager,
SwapSpace: int32(c.SwapSpace),
MaxModelLen: int32(c.MaxModelLen),
MMProj: c.MMProj,
YarnExtFactor: c.YarnExtFactor,
YarnAttnFactor: c.YarnAttnFactor,
YarnBetaFast: c.YarnBetaFast,
YarnBetaSlow: c.YarnBetaSlow,
LoraAdapter: c.LoraAdapter,
LoraBase: c.LoraBase,
LoraScale: c.LoraScale,
NGQA: c.NGQA,
RMSNormEps: c.RMSNormEps,
F16Memory: c.F16,
MLock: c.MMlock,
RopeFreqBase: c.RopeFreqBase,
RopeScaling: c.RopeScaling,
Type: c.ModelType,
RopeFreqScale: c.RopeFreqScale,
NUMA: c.NUMA,
Embeddings: c.Embeddings,
LowVRAM: c.LowVRAM,
NGPULayers: int32(c.NGPULayers),
MMap: c.MMap,
MainGPU: c.MainGPU,
Threads: int32(c.Threads),
TensorSplit: c.TensorSplit,
// AutoGPTQ
ModelBaseName: c.AutoGPTQ.ModelBaseName,
Device: c.AutoGPTQ.Device,