release

2025-06-13 00:41:33 +08:00
parent 98a1551a7d
commit 135d1b38a2
5 changed files with 65 additions and 8 deletions
--- a/bench.py
+++ b/bench.py
@@ -24,4 +24,4 @@ llm.generate(prompt_token_ids, sampling_params)
 t = (time.time() - t)
 total_tokens = sum(sp.max_tokens for sp in sampling_params)
 throughput = total_tokens / t
-print(f"Total: {total_tokens}, Time: {t:.2f}s, Throughput: {throughput: .2f}")
+print(f"Total: {total_tokens}tok, Time: {t:.2f}s, Throughput: {throughput: .2f}tok/s")