c9ac39fc1e
* Add Llama 3.2 to iGPU Perf (#12200) * Add Llama 3.2 to iGPU Perf * Downgrade accelerate after step * Temporarily disable model for test * Temporarily change ERRORLEVEL check (#12201) * Restore llama3.2 perf (#12206) * Revert "Temporarily change ERRORLEVEL check" This reverts commit 909dbbc930ab4283737161a55bb32006e6ca1991. * Revert "Temporarily disable model for test" This reverts commit 95322dc3c6429aa836f21bda0b5ba8d9b48592f8. --------- Co-authored-by: Jin, Qiao <89779290+JinBridger@users.noreply.github.com>
14 lines
525 B
YAML
14 lines
525 B
YAML
repo_id:
|
|
- 'meta-llama/Llama-3.2-1B-Instruct'
|
|
- 'meta-llama/Llama-3.2-3B-Instruct'
|
|
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)
|
|
batch_size: 1 # default to 1
|
|
in_out_pairs:
|
|
- '4096-512'
|
|
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)
|