| 1 | [ |
| 2 | { |
| 3 | "test_name": "throughput_llama8B_tp1", |
| 4 | "parameters": { |
| 5 | "model": "meta-llama/Meta-Llama-3.1-8B-Instruct", |
| 6 | "tensor_parallel_size": 1, |
| 7 | "load_format": "dummy", |
| 8 | "dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json", |
| 9 | "num_prompts": 200, |
| 10 | "backend": "vllm" |
| 11 | } |
| 12 | }, |
| 13 | { |
| 14 | "test_name": "throughput_llama70B_tp4", |
| 15 | "parameters": { |
| 16 | "model": "meta-llama/Meta-Llama-3.1-70B-Instruct", |
| 17 | "tensor_parallel_size": 4, |
| 18 | "load_format": "dummy", |
| 19 | "dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json", |
| 20 | "num_prompts": 200, |
| 21 | "backend": "vllm" |
| 22 | } |
| 23 | }, |
| 24 | { |
| 25 | "test_name": "throughput_mixtral8x7B_tp2", |
| 26 | "parameters": { |
| 27 | "model": "mistralai/Mixtral-8x7B-Instruct-v0.1", |
| 28 | "tensor_parallel_size": 2, |
| 29 | "load_format": "dummy", |
| 30 | "dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json", |
| 31 | "num_prompts": 200, |
| 32 | "backend": "vllm" |
| 33 | } |
| 34 | } |
| 35 | ] |