Continous batching for single GPU LLM inference #3164

Sign in to view logs

Triggered via pull request October 3, 2023 20:54

mreso

synchronize #2628

feature/continous_batching_for_streaming

Status Success

Total duration 45m 45s

Artifacts –

ci_cpu.yml

on: pull_request

Matrix: ci-cpu

Annotations

1 warning

ci-cpu (macOS-latest)

Attempt 1 failed. Reason: Child_process exited with error code 1