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

* 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

View file

@ -69,6 +69,13 @@ func (ml *ModelLoader) grpcModel(backend string, o *Options) func(string, string
return fmt.Sprintf("127.0.0.1:%d", port), nil
}
// If no specific model path is set for transformers/HF, set it to the model path
for _, env := range []string{"HF_HOME", "TRANSFORMERS_CACHE", "HUGGINGFACE_HUB_CACHE"} {
if os.Getenv(env) == "" {
os.Setenv(env, ml.ModelPath)
}
}
// Check if the backend is provided as external
if uri, ok := o.externalBackends[backend]; ok {
log.Debug().Msgf("Loading external backend: %s", uri)