Files
nano-vllm/bench_offload.py
Zijie Tian 4467e1f654 🔧 chore: add --block-size argument to bench_offload.py
Allow configuring KV cache block size for benchmarking different
chunk sizes (default: 1024, can set to 4096 for larger chunks).

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>
2026-01-27 09:07:44 +08:00

6.0 KiB