894d0aaf5e
* trigger pr temparorily * Saparate benchmark run for win igpu based in in-out pairs * Rename fix * Test workflow * Small fix * Skip generation of html for now * Change back to nightly triggered
12 lines
452 B
YAML
12 lines
452 B
YAML
repo_id:
|
|
- 'mistralai/Mistral-7B-Instruct-v0.1'
|
|
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:
|
|
- '32-256'
|
|
test_api:
|
|
- "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)
|