[Doc]Add instruction for profiling with bench_one_batch (#5581)

This commit is contained in:
Baizhou Zhang
2025-04-20 14:05:36 -07:00
committed by GitHub
parent bca832c7c6
commit b54b5a96e4
2 changed files with 7 additions and 2 deletions

View File

@@ -396,7 +396,7 @@ def latency_test_run_once(
decode_latencies.append(latency)
if i < 5:
rank_print(
f"Decode. latency: {latency:6.5f} s, throughput: {throughput:9.2f} token/s"
f"Decode. Batch size: {batch_size}, latency: {latency:6.5f} s, throughput: {throughput:9.2f} token/s"
)
if profile: