Files
nano-vllm/tests/test_ruler.py
Zijie Tian 45efcf0db1 feat: add --dtype parameter to test_ruler.py
Support models with float32 default dtype (e.g., Nemotron).
FlashAttention requires fp16/bf16, so dtype must be specified.

Usage: --dtype bfloat16

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-28 13:56:15 +08:00

22 KiB