mirror of https://github.com/wassname/vllm.git synced 2026-07-01 00:36:31 +08:00

Files

T

Varun Sundar Rabindranath 35e9c12bfa [Kernel] Tuned int8 Cutlass Kernels for SM75 (T4) (#6996 )

Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

2024-07-31 14:40:32 -07:00

2024-07-31 14:40:32 -07:00

2024-07-27 17:52:33 -04:00

2024-06-20 17:00:13 -06:00

backend_request_func.py

2024-07-11 07:04:05 +00:00

benchmark_latency.py

2024-07-22 10:13:53 -07:00

benchmark_prefix_caching.py

2024-06-20 17:00:13 -06:00

benchmark_serving.py

2024-07-14 19:27:01 -07:00

benchmark_throughput.py

2024-06-28 13:50:16 +00:00

launch_tgi_server.sh

2024-05-20 20:16:57 +00:00

README.md

2023-06-17 03:07:40 -07:00

sonnet.txt

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