Skip to content
CI - sharktank perplexity short

Use Trie and Base Caching in SGL Benchmark #333

Sign in to view logs

Use Trie and Base Caching in SGL Benchmark

Use Trie and Base Caching in SGL Benchmark #333

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Llama3.1 8B FP16 (3.11, llama-mi300x-3)
4m 2s
4m 2s