c998f5f2ba
* Temp enable PR * Enable tests for 256-64 * Try again 128-64 * Empty cache after each iteration for igpu benchmark scripts * Try tests for 512 * change order for 512 * Skip chatglm3 and llama2 for now * Separate tests for 512-64 * Small fix * Further fixes * Change back to nightly again
32 lines
1.1 KiB
YAML
32 lines
1.1 KiB
YAML
repo_id:
|
|
- 'THUDM/chatglm2-6b'
|
|
# - 'THUDM/chatglm3-6b'
|
|
# - 'baichuan-inc/Baichuan2-7B-Chat'
|
|
# - 'internlm/internlm-chat-7b-8k'
|
|
# - 'Qwen/Qwen-7B-Chat-10-12'
|
|
# - 'BAAI/AquilaChat2-7B'
|
|
- '01-ai/Yi-6B'
|
|
# - 'meta-llama/Llama-2-7b-chat-hf'
|
|
# - 'WisdomShell/CodeShell-7B-Chat'
|
|
- 'tiiuae/falcon-7b-instruct-with-patch'
|
|
- 'mosaicml/mpt-7b-chat'
|
|
# - 'liuhaotian/llava-v1.5-7b'
|
|
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:
|
|
- '512-64'
|
|
# - '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
|
|
- "transformer_int4_gpu_win" # on Intel GPU for Windows (catch GPU peak memory)
|
|
cpu_embedding: True # whether put embedding to CPU (only avaiable now for gpu win related test_api)
|