dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat(diffusers): allow multiple lora adapters (#4081)

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-11-05 15:14:33 +01:00 • committed by GitHub
parent 20cd8814c1
commit 947224b952
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 39 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

36
core/config/backend_config.go
View file

@ -134,23 +134,25 @@ type LLMConfig struct {
TrimSpace []string `yaml:"trimspace"`
TrimSuffix []string `yaml:"trimsuffix"`
ContextSize *int `yaml:"context_size"`
NUMA bool `yaml:"numa"`
LoraAdapter string `yaml:"lora_adapter"`
LoraBase string `yaml:"lora_base"`
LoraScale float32 `yaml:"lora_scale"`
NoMulMatQ bool `yaml:"no_mulmatq"`
DraftModel string `yaml:"draft_model"`
NDraft int32 `yaml:"n_draft"`
Quantization string `yaml:"quantization"`
LoadFormat string `yaml:"load_format"`
GPUMemoryUtilization float32 `yaml:"gpu_memory_utilization"` // vLLM
TrustRemoteCode bool `yaml:"trust_remote_code"` // vLLM
EnforceEager bool `yaml:"enforce_eager"` // vLLM
SwapSpace int `yaml:"swap_space"` // vLLM
MaxModelLen int `yaml:"max_model_len"` // vLLM
TensorParallelSize int `yaml:"tensor_parallel_size"` // vLLM
MMProj string `yaml:"mmproj"`
ContextSize *int `yaml:"context_size"`
NUMA bool `yaml:"numa"`
LoraAdapter string `yaml:"lora_adapter"`
LoraBase string `yaml:"lora_base"`
LoraAdapters []string `yaml:"lora_adapters"`
LoraScales []float32 `yaml:"lora_scales"`
LoraScale float32 `yaml:"lora_scale"`
NoMulMatQ bool `yaml:"no_mulmatq"`
DraftModel string `yaml:"draft_model"`
NDraft int32 `yaml:"n_draft"`
Quantization string `yaml:"quantization"`
LoadFormat string `yaml:"load_format"`
GPUMemoryUtilization float32 `yaml:"gpu_memory_utilization"` // vLLM
TrustRemoteCode bool `yaml:"trust_remote_code"` // vLLM
EnforceEager bool `yaml:"enforce_eager"` // vLLM
SwapSpace int `yaml:"swap_space"` // vLLM
MaxModelLen int `yaml:"max_model_len"` // vLLM
TensorParallelSize int `yaml:"tensor_parallel_size"` // vLLM
MMProj string `yaml:"mmproj"`
FlashAttention bool `yaml:"flash_attention"`
NoKVOffloading bool `yaml:"no_kv_offloading"`