Skip to content

[Misc] Separate total and output tokens in benchmark_throughput.py #8914

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Oct 23, 2024
Merged

[Misc] Separate total and output tokens in benchmark_throughput.py #8914

Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d5a66d6
Separate total and output tokens in benchmark_throughput.py
mgoin Sep 27, 2024
b47ff92
Add max-num-seqs
mgoin Sep 27, 2024
5e80285
Merge branch 'main' into separate-total-output-tokens-throughput
mgoin Oct 3, 2024
1a33510
Lint
mgoin Oct 3, 2024
19cec43
Merge branch 'main' into separate-total-output-tokens-throughput
mgoin Oct 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 15 additions & 2 deletions benchmarks/benchmark_throughput.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,7 @@ def run_vllm(
enable_prefix_caching: bool,
enable_chunked_prefill: bool,
max_num_batched_tokens: int,
max_num_seqs: int,
distributed_executor_backend: Optional[str],
gpu_memory_utilization: float = 0.9,
num_scheduler_steps: int = 1,
Expand Down Expand Up @@ -111,6 +112,7 @@ def run_vllm(
download_dir=download_dir,
enable_chunked_prefill=enable_chunked_prefill,
max_num_batched_tokens=max_num_batched_tokens,
max_num_seqs=max_num_seqs,
distributed_executor_backend=distributed_executor_backend,
load_format=load_format,
num_scheduler_steps=num_scheduler_steps,
Expand Down Expand Up @@ -172,6 +174,7 @@ async def run_vllm_async(
enable_prefix_caching: bool,
enable_chunked_prefill: bool,
max_num_batched_tokens: int,
max_num_seqs: int,
distributed_executor_backend: Optional[str],
gpu_memory_utilization: float = 0.9,
num_scheduler_steps: int = 1,
Expand Down Expand Up @@ -200,6 +203,7 @@ async def run_vllm_async(
download_dir=download_dir,
enable_chunked_prefill=enable_chunked_prefill,
max_num_batched_tokens=max_num_batched_tokens,
max_num_seqs=max_num_seqs,
distributed_executor_backend=distributed_executor_backend,
load_format=load_format,
num_scheduler_steps=num_scheduler_steps,
Expand Down Expand Up @@ -341,7 +345,8 @@ def main(args: argparse.Namespace):
args.enforce_eager, args.kv_cache_dtype,
args.quantization_param_path, args.device,
args.enable_prefix_caching, args.enable_chunked_prefill,
args.max_num_batched_tokens, args.distributed_executor_backend,
args.max_num_batched_tokens, args.max_num_seqs,
args.distributed_executor_backend,
args.gpu_memory_utilization, args.num_scheduler_steps,
args.use_v2_block_manager, args.download_dir, args.load_format,
args.disable_async_output_proc
Expand All @@ -364,8 +369,11 @@ def main(args: argparse.Namespace):
raise ValueError(f"Unknown backend: {args.backend}")
total_num_tokens = sum(prompt_len + output_len
for _, prompt_len, output_len in requests)
total_output_tokens = sum(output_len
for _, _, output_len in requests)
print(f"Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
f"{total_num_tokens / elapsed_time:.2f} tokens/s")
f"{total_num_tokens / elapsed_time:.2f} total tokens/s, "
f"{total_output_tokens / elapsed_time:.2f} output tokens/s")

# Output JSON results if specified
if args.output_json:
Expand Down Expand Up @@ -491,6 +499,11 @@ def main(args: argparse.Namespace):
default=None,
help='maximum number of batched tokens per '
'iteration')
parser.add_argument('--max-num-seqs',
type=int,
default=None,
help='maximum number of sequences per '
'iteration')
parser.add_argument('--download-dir',
type=str,
default=None,
Expand Down
Loading