| 1 | [ |
| 2 | { |
| 3 | "test_name": "latency_llama8B_tp1", |
| 4 | "parameters": { |
| 5 | "model": "meta-llama/Meta-Llama-3.1-8B-Instruct", |
| 6 | "tensor_parallel_size": 1, |
| 7 | "load_format": "dummy", |
| 8 | "num_iters_warmup": 5, |
| 9 | "num_iters": 15 |
| 10 | } |
| 11 | }, |
| 12 | { |
| 13 | "test_name": "latency_llama70B_tp4", |
| 14 | "parameters": { |
| 15 | "model": "meta-llama/Meta-Llama-3.1-70B-Instruct", |
| 16 | "tensor_parallel_size": 4, |
| 17 | "load_format": "dummy", |
| 18 | "num-iters-warmup": 5, |
| 19 | "num-iters": 15 |
| 20 | } |
| 21 | }, |
| 22 | { |
| 23 | "test_name": "latency_mixtral8x7B_tp2", |
| 24 | "parameters": { |
| 25 | "model": "mistralai/Mixtral-8x7B-Instruct-v0.1", |
| 26 | "tensor_parallel_size": 2, |
| 27 | "load_format": "dummy", |
| 28 | "num-iters-warmup": 5, |
| 29 | "num-iters": 15 |
| 30 | } |
| 31 | } |
| 32 | ] |