Skip to content

Commit

Permalink
Add the ability to benchmark multiple models concurrently.
Browse files Browse the repository at this point in the history
This is useful for benchmarking multiple LoRA adapters.
- Also fix the latency_throughput_curve.sh to parse non-integer request
  rate properly.
- Also added "errors" to the benchmark results.
  • Loading branch information
liu-cong committed Oct 17, 2024
1 parent 4fdcca6 commit b0be375
Show file tree
Hide file tree
Showing 7 changed files with 227 additions and 113 deletions.
Loading

0 comments on commit b0be375

Please sign in to comment.