zijie-tian/nano-vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

✨ feat: add --model argument to bench.py for configurable model path

Browse Source 
Previously bench.py had a hardcoded model path. Now it accepts --model
argument (default: Llama-3.1-8B-Instruct) to align with bench_offload.py.

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
This commit is contained in:
Zijie Tian
2026-01-27 04:36:17 +08:00
parent 73c9dc46ff
commit c717072f31
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
bench.py
View File

@@ -41,6 +41,8 @@ def bench_prefill(llm, num_seqs, input_len):
def main(): def main():
import argparse import argparse
parser = argparse.ArgumentParser(description="Benchmark nanovllm GPU performance") parser = argparse.ArgumentParser(description="Benchmark nanovllm GPU performance")
parser.add_argument("--model", type=str, default="~/models/Llama-3.1-8B-Instruct",
help="Model path (default: ~/models/Llama-3.1-8B-Instruct)")
parser.add_argument("--input-len", type=int, default=None, help="Input length in tokens") parser.add_argument("--input-len", type=int, default=None, help="Input length in tokens")
parser.add_argument("--output-len", type=int, default=64, help="Output length for decode benchmark (default: 64)") parser.add_argument("--output-len", type=int, default=64, help="Output length for decode benchmark (default: 64)")
parser.add_argument("--max-len", type=int, default=32*1024, help="Max model length (default: 32K)") parser.add_argument("--max-len", type=int, default=32*1024, help="Max model length (default: 32K)")
@@ -48,7 +50,7 @@ def main():
parser.add_argument("--bench-all", action="store_true", help="Run both prefill and decode benchmarks") parser.add_argument("--bench-all", action="store_true", help="Run both prefill and decode benchmarks")
args = parser.parse_args() args = parser.parse_args()
path = os.path.expanduser("~/models/Qwen3-4B-Instruct-2507/") path = os.path.expanduser(args.model)
max_len = args.max_len max_len = args.max_len
print(f"\n[nanovllm GPU] max_len={max_len}") print(f"\n[nanovllm GPU] max_len={max_len}")