8982ab73d5
* Add transformer4.38.2 test to igpu benchmark (#11529) * add transformer4.38.1 test to igpu benchmark * use transformers4.38.2 & fix csv name error in 4.38 workflow * add model Yi-6B-Chat & remove temporarily most models --------- Co-authored-by: ATMxsp01 <shou.xu@intel.com> * filter some errorlevel (#11541) Co-authored-by: ATMxsp01 <shou.xu@intel.com> * Restore the temporarily removed models in iGPU-perf (#11544) * filter some errorlevel * restore the temporarily removed models in iGPU-perf --------- Co-authored-by: ATMxsp01 <shou.xu@intel.com> --------- Co-authored-by: Xu, Shuo <100334393+ATMxsp01@users.noreply.github.com> Co-authored-by: ATMxsp01 <shou.xu@intel.com>
14 lines
507 B
YAML
14 lines
507 B
YAML
repo_id:
|
|
- 'stabilityai/stablelm-zephyr-3b'
|
|
#- 'google/gemma-7b-it'
|
|
local_model_hub: 'path to your local model hub'
|
|
warm_up: 3
|
|
num_trials: 5
|
|
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'
|
|
test_api:
|
|
- "transformer_int4_fp16_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)
|