7f8c5b410b
* add entrypoint.sh * add quickstart * remove entrypoint * update * Install related library of benchmarking * update * print out results * update docs * minor update * update * update quickstart * update * update * update * update * update * update * add chat & example section * add more details * minor update * rename quickstart * update * minor update * update * update config.yaml * update readme * use --gpu * add tips * minor update * update
39 lines
2.9 KiB
YAML
39 lines
2.9 KiB
YAML
repo_id:
|
|
# - 'THUDM/chatglm2-6b'
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
# - 'liuhaotian/llava-v1.5-7b' # requires a LLAVA_REPO_DIR env variables pointing to the llava dir; added only for gpu win related test_api now
|
|
local_model_hub: 'path to your local model hub'
|
|
warm_up: 1 # must set >=2 when run "pipeline_parallel_gpu" test_api
|
|
num_trials: 3
|
|
num_beams: 1 # default to greedy search
|
|
low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
|
|
batch_size: 1 # default to 1
|
|
in_out_pairs:
|
|
- '32-32'
|
|
- '1024-128'
|
|
test_api:
|
|
- "transformer_int4_gpu" # on Intel GPU, transformer-like API, (qtype=int4)
|
|
# - "transformer_int4_gpu_win" # on Intel GPU for Windows, transformer-like API, (qtype=int4)
|
|
# - "transformer_int4_fp16_gpu" # on Intel GPU, transformer-like API, (qtype=int4), (dtype=fp16)
|
|
# - "transformer_int4_fp16_gpu_win" # on Intel GPU for Windows, transformer-like API, (qtype=int4), (dtype=fp16)
|
|
# - "transformer_int4_loadlowbit_gpu_win" # on Intel GPU for Windows, transformer-like API, (qtype=int4), use load_low_bit API. Please make sure you have used the save.py to save the converted low bit model
|
|
# - "ipex_fp16_gpu" # on Intel GPU, use native transformers API, (dtype=fp16)
|
|
# - "bigdl_fp16_gpu" # on Intel GPU, use ipex-llm transformers API, (dtype=fp16), (qtype=fp16)
|
|
# - "optimize_model_gpu" # on Intel GPU, can optimize any pytorch models include transformer model
|
|
# - "deepspeed_optimize_model_gpu" # on Intel GPU, deepspeed autotp inference
|
|
# - "pipeline_parallel_gpu" # on Intel GPU, pipeline parallel inference
|
|
# - "speculative_gpu" # on Intel GPU, inference with self-speculative decoding
|
|
# - "transformer_int4" # on Intel CPU, transformer-like API, (qtype=int4)
|
|
# - "native_int4" # on Intel CPU
|
|
# - "optimize_model" # on Intel CPU, can optimize any pytorch models include transformer model
|
|
# - "pytorch_autocast_bf16" # on Intel CPU
|
|
# - "transformer_autocast_bf16" # on Intel CPU
|
|
# - "bigdl_ipex_bf16" # on Intel CPU, (qtype=bf16)
|
|
# - "bigdl_ipex_int4" # on Intel CPU, (qtype=int4)
|
|
# - "bigdl_ipex_int8" # on Intel CPU, (qtype=int8)
|
|
# - "speculative_cpu" # on Intel CPU, inference with self-speculative decoding
|
|
# - "deepspeed_transformer_int4_cpu" # on Intel CPU, deepspeed autotp inference
|
|
cpu_embedding: False # whether put embedding to CPU
|
|
streaming: False # whether output in streaming way (only avaiable now for gpu win related test_api)
|
|
use_fp16_torch_dtype: True # whether use fp16 for non-linear layer (only avaiable now for "pipeline_parallel_gpu" test_api)
|
|
n_gpu: 2 # number of GPUs to use (only avaiable now for "pipeline_parallel_gpu" test_api)
|