dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-25 13:04:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

feat(intel): add diffusers/transformers support (#1746)

Browse source 
* feat(intel): add diffusers support

* try to consume upstream container image

* Debug

* Manually install deps

* Map transformers/hf cache dir to modelpath if not specified

* fix(compel): update initialization, pass by all gRPC options

* fix: add dependencies, implement transformers for xpu

* base it from the oneapi image

* Add pillow

* set threads if specified when launching the API

* Skip conda install if intel

* defaults to non-intel

* ci: add to pipelines

* prepare compel only if enabled

* Skip conda install if intel

* fix cleanup

* Disable compel by default

* Install torch 2.1.0 with Intel

* Skip conda on some setups

* Detect python

* Quiet output

* Do not override system python with conda

* Prefer python3

* Fixups

* exllama2: do not install without conda (overrides pytorch version)

* exllama/exllama2: do not install if not using cuda

* Add missing dataset dependency

* Small fixups, symlink to python, add requirements

* Add neural_speed to the deps

* correctly handle model offloading

* fix: device_map == xpu

* go back at calling python, fixed at dockerfile level

* Exllama2 restricted to only nvidia gpus

* Tokenizer to xpu
This commit is contained in:
Ettore Di Giacinto 2024-03-07 14:37:45 +01:00 • committed by GitHub
parent ad6fd7a991
commit 5d1018495f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 250 additions and 81 deletions
Download patch file Download diff file Expand all files Collapse all files

18
core/backend/options.go
View file

@ -40,11 +40,23 @@ func gRPCModelOpts(c config.BackendConfig) *pb.ModelOptions {
}
return &pb.ModelOptions{
CUDA: c.CUDA || c.Diffusers.CUDA,
SchedulerType: c.Diffusers.SchedulerType,
PipelineType: c.Diffusers.PipelineType,
CFGScale: c.Diffusers.CFGScale,
LoraAdapter: c.LoraAdapter,
LoraScale: c.LoraScale,
F16Memory: c.F16,
LoraBase: c.LoraBase,
IMG2IMG: c.Diffusers.IMG2IMG,
CLIPModel: c.Diffusers.ClipModel,
CLIPSubfolder: c.Diffusers.ClipSubFolder,
CLIPSkip: int32(c.Diffusers.ClipSkip),
ControlNet: c.Diffusers.ControlNet,
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,
@ -58,12 +70,8 @@ func gRPCModelOpts(c config.BackendConfig) *pb.ModelOptions {
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,