af94058203
* [LLM] Support CPU Deepspeed distributed inference * Update run_deepspeed.py * Rename * fix style * add new codes * refine * remove annotated codes * refine * Update README.md * refine doc and example code
22 lines
603 B
YAML
22 lines
603 B
YAML
repo_id:
|
|
- 'THUDM/chatglm-6b'
|
|
- 'THUDM/chatglm2-6b'
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
local_model_hub: 'path to your local model hub'
|
|
warm_up: 1
|
|
num_trials: 3
|
|
num_beams: 1 # default to greedy search
|
|
low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
|
|
in_out_pairs:
|
|
- '32-32'
|
|
- '1024-128'
|
|
test_api:
|
|
- "transformer_int4"
|
|
- "native_int4"
|
|
- "optimize_model"
|
|
- "pytorch_autocast_bf16"
|
|
# - "ipex_fp16_gpu" # on Intel GPU
|
|
# - "transformer_int4_gpu" # on Intel GPU
|
|
# - "optimize_model_gpu" # on Intel GPU
|
|
# - "deepspeed_transformer_int4_cpu" # on Intel SPR Server
|
|
|