5cfb4c4f5b
* add arc stable version regression test * empty gpu mem between different models * triger ci * comment spr test * triger ci * address kai's comments and disable ci * merge fp8 and int4 * disable ci
18 lines
536 B
YAML
18 lines
536 B
YAML
repo_id:
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
- 'THUDM/chatglm2-6b'
|
|
- 'THUDM/chatglm3-6b'
|
|
- 'baichuan-inc/Baichuan2-7B-Chat'
|
|
- 'Qwen/Qwen-7B-Chat'
|
|
local_model_hub: '/mnt/disk1/models'
|
|
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'
|
|
- '2048-256'
|
|
test_api:
|
|
- "transformer_int4_gpu" # on Intel GPU
|
|
cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
|