AlpinDale 5b5e6dc359 chore: add batch size 1536 and 3072 to moe benchmark vor 7 Monaten
..
attention.py e1f3fd1e02 fix: test units (#201) vor 1 Jahr
backend_request_func.py 89ee54dcff update dockerfile and enhance serving benchmark vor 7 Monaten
benchmark_moe.py 5b5e6dc359 chore: add batch size 1536 and 3072 to moe benchmark vor 7 Monaten
hashing.py c6a501f682 add multiprocessing executor; make ray optional vor 7 Monaten
latency.py e1f3fd1e02 fix: test units (#201) vor 1 Jahr
launch_tgi.sh 4d04ade9ef feat: fine-grained seeds (#279) vor 1 Jahr
serving.py 89ee54dcff update dockerfile and enhance serving benchmark vor 7 Monaten
sonnet.txt 89ee54dcff update dockerfile and enhance serving benchmark vor 7 Monaten
throughput.py 033797fd55 refactor throughput benchmark script vor 7 Monaten