inference/research
verifiedhigh · 0.94updated 2026-10-04

SGLang KV-transfer allocation histogram

sglang · histogram

Fields

id
metric-exposures/w3m-sglang-sglang-kv-transfer-alloc-ms
Metric name
sglang:kv_transfer_alloc_ms
Metric type
histogram
Unit
milliseconds
Exposure
prometheus
Endpoint
:30000/metrics
Histogram buckets
12510255010025050010002500
Labels
model_nameengine_typetp_rankpp_rankmoe_ep_rank
Enabled by default
no
Phase scoped
yes
notes
SGLang main, python/sglang/srt/observability/metrics_collector.py, read 2026-10-04. NOT ON BY DEFAULT: nothing is exported unless --enable-metrics (ServerArgs default False), which is also the only thing that mounts /metrics on the server port. Label keys are model_name, engine_type, tp_rank, pp_rank, moe_ep_rank (plus dp_rank under data parallelism, priority under priority scheduling, and anything in extra_metric_labels). Bucket ladders are overridable per histogram via get_histogram_conf_from_env. Time spent allocating transfer buffers.

Notes

SGLang main, python/sglang/srt/observability/metrics_collector.py, read 2026-10-04. NOT ON BY DEFAULT: nothing is exported unless --enable-metrics (ServerArgs default False), which is also the only thing that mounts /metrics on the server port. Label keys are model_name, engine_type, tp_rank, pp_rank, moe_ep_rank (plus dp_rank under data parallelism, priority under priority scheduling, and anything in extra_metric_labels). Bucket ladders are overridable per histogram via get_histogram_conf_from_env. Time spent allocating transfer buffers.

Cross-references