History

Elinx fe3b5bbc23 [Bugfix] fix output parsing error for trtllm backend (#4137 ) Co-authored-by: Roger Wang <ywang@roblox.com>		2024-04-17 11:07:23 +00:00
..
kernels	[Misc] Add indirection layer for custom ops (#3913 )	2024-04-10 20:26:07 -07:00
backend_request_func.py	[Bugfix] fix output parsing error for trtllm backend (#4137 )	2024-04-17 11:07:23 +00:00
benchmark_latency.py	[Core][5/N] Fully working chunked prefill e2e (#3884 )	2024-04-10 17:56:48 -07:00
benchmark_prefix_caching.py	[CI] Try introducing isort. (#3495 )	2024-03-25 07:59:47 -07:00
benchmark_serving.py	[Bugfix] Fix args in benchmark_serving (#3836 )	2024-04-04 07:41:05 +00:00
benchmark_throughput.py	[Core][5/N] Fully working chunked prefill e2e (#3884 )	2024-04-10 17:56:48 -07:00
launch_tgi_server.sh	Serving Benchmark Refactoring (#2433 )	2024-02-12 22:53:00 -08:00
README.md	Change the name to vLLM (#150 )	2023-06-17 03:07:40 -07:00
sonnet.txt	feat(benchmarks): Add Prefix Caching Benchmark to Serving Benchmark (#3277 )	2024-03-27 13:39:26 -07:00

Benchmarking vLLM

Downloading the ShareGPT dataset

You can download the dataset by running:

wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json