Skip to content

Overlap GPU prefill token chunks with bounded KV copies - #254

Closed
gspark-etri wants to merge 4 commits into
feat/249-pd-stage-metricsfrom
perf/47-chunk-copy
Closed

Overlap GPU prefill token chunks with bounded KV copies#254
gspark-etri wants to merge 4 commits into
feat/249-pd-stage-metricsfrom
perf/47-chunk-copy

exp: record reverse-order GPU copy-overlap serving results (#47)

098169b
Select commit
Loading
Failed to load commit list.

There are no checks for this commit