cca84b0a64
* update llm benchmark scripts. * change tranformer_bf16 to pytorch_autocast_bf16. * add autocast in transformer int4. * revert autocast. * add "pytorch_autocast_bf16" to doc * fix comments.
17 lines
No EOL
381 B
YAML
17 lines
No EOL
381 B
YAML
repo_id:
|
|
- 'THUDM/chatglm-6b'
|
|
- 'THUDM/chatglm2-6b'
|
|
- 'meta-llama/Llama-2-7b-chat-hf'
|
|
local_model_hub: 'path to your local model hub'
|
|
warm_up: 1
|
|
num_trials: 3
|
|
in_out_pairs:
|
|
- '32-32'
|
|
- '1024-128'
|
|
test_api:
|
|
- "transformer_int4"
|
|
- "native_int4"
|
|
- "optimize_model"
|
|
- "pytorch_autocast_bf16"
|
|
# - "transformer_int4_gpu" # on arc
|
|
# - "optimize_model_gpu" # on arc |