Schema.ai· vLLM
vLLM v0.23.0API up

vLLM v0.23.0 v1 metrics perf.py

Type
source_file
Publisher
vllm-project
Relationship
first_party
Version
vLLM v0.23.0
Retrieved
Jul 9
Local snapshot
corpus/domains/vllm/core-v0/evidence/snapshots/vllm-code-v0230-v1-metrics-perf.py
SHA-256
c16dad2f8fa7b1c7

Claims citing this source (0)

No claims cite this source yet.

Metrics grounded in this source (3)

NameDescriptionLocator
estimated_flops_per_gpu_totalCounter of estimated floating point operations per GPU, for Model FLOPs Utilization calculations.vllm/v1/metrics/perf.py:1286-1296
estimated_read_bytes_per_gpu_totalCounter of estimated bytes read from memory per GPU, for Model FLOPs Utilization calculations.vllm/v1/metrics/perf.py:1298-1308
estimated_write_bytes_per_gpu_totalCounter of estimated bytes written to memory per GPU, for Model FLOPs Utilization calculations.vllm/v1/metrics/perf.py:1310-1320

View all 3 in Metrics