vllm
vllm copied to clipboard
Benchmark: add H100 suite
I have recently added an H100 agent which will be online for 12 hours per day. Let's test it out.
Successful build: https://buildkite.com/vllm/performance-benchmark/builds/4258
Can I use this for some fp8 test - especially Mixtral
@KuntaiDu can you please review this? I think I got it working (see link in the description) by adding bunch of clean up in the shell script
this is awesome, thanks for adding