github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-29 21:46:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

[misc] update pre-commit and run all files (#4752)

Browse Source 
* [misc] update pre-commit

* [misc] run pre-commit

* [misc] remove useless configuration files

* [misc] ignore cuda for clang-format
This commit is contained in:
Hongxin Liu
2023-09-19 14:20:26 +08:00
committed by GitHub
parent 3c6b831c26
commit 079bf3cb26
1268 changed files with 50037 additions and 38444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
examples/inference/bench_bloom.py
View File

@@ -11,7 +11,7 @@ from colossalai.logging import disable_existing_loggers
from colossalai.shardformer import ShardConfig
from colossalai.testing import clear_cache_before_run, rerun_if_address_is_in_use, spawn
os.environ['TRANSFORMERS_NO_ADVISORY_WARNINGS'] = 'true'
os.environ["TRANSFORMERS_NO_ADVISORY_WARNINGS"] = "true"
def print_perf_stats(latency_set, config, bs, warmup=3):
@@ -25,7 +25,7 @@ def print_perf_stats(latency_set, config, bs, warmup=3):
avg = sum(latency_set) / count
num_layers = getattr(config, "num_layers", config.num_hidden_layers)
num_parameters = num_layers * config.hidden_size * config.hidden_size * 12
num_bytes = 2 # float16
num_bytes = 2 # float16
print("Avg Per Token Latency: {0:8.2f} ms".format(avg * 1000))
print("Avg BW: {0:8.2f} GB/s".format(1 / avg * num_parameters * num_bytes / 1e9))
@@ -53,7 +53,7 @@ def bench_bloom(args):
generate_kwargs = dict(max_new_tokens=max_output_len, do_sample=False)
input_tokens = {
"input_ids": torch.randint(10, 1000, (max_batch_size, max_input_len)),
"attention_mask": torch.ones((max_batch_size, max_input_len))
"attention_mask": torch.ones((max_batch_size, max_input_len)),
}
for t in input_tokens:
if torch.is_tensor(input_tokens[t]):
@@ -77,7 +77,7 @@ def bench_bloom(args):
def check_bloom(rank, world_size, port, args):
disable_existing_loggers()
colossalai.launch(config={}, rank=rank, world_size=world_size, host='localhost', port=port, backend='nccl')
colossalai.launch(config={}, rank=rank, world_size=world_size, host="localhost", port=port, backend="nccl")
bench_bloom(args)
@@ -89,11 +89,11 @@ def test_bloom(args):
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('-p', '--path', type=str, help='Model path', required=True)
parser.add_argument('-tp', '--tp_size', type=int, default=1, help='Tensor parallel size')
parser.add_argument('-b', '--batch_size', type=int, default=16, help='Maximum batch size')
parser.add_argument('--input_len', type=int, default=1024, help='Maximum input length')
parser.add_argument('--output_len', type=int, default=128, help='Maximum output length')
parser.add_argument("-p", "--path", type=str, help="Model path", required=True)
parser.add_argument("-tp", "--tp_size", type=int, default=1, help="Tensor parallel size")
parser.add_argument("-b", "--batch_size", type=int, default=16, help="Maximum batch size")
parser.add_argument("--input_len", type=int, default=1024, help="Maximum input length")
parser.add_argument("--output_len", type=int, default=128, help="Maximum output length")
args = parser.parse_args()