Skip to content

Commit

Permalink
Merge pull request #7 from arc53/no6
Browse files Browse the repository at this point in the history
feat: A10G benchmark
  • Loading branch information
dartpain authored Aug 20, 2024
2 parents 9e45393 + a4c6c6d commit 9404054
Showing 1 changed file with 18 additions and 0 deletions.
18 changes: 18 additions & 0 deletions benchmarks/Meta-Llama-3.1-8B-Instruct/A10G/20-08-2024.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
{
"date": "20240820-143000",
"provider": "aws",
"gpu": "NVIDIA A10G",
"cost_per_hour": 2.84,
"backend": "vllm",
"model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tokenizer_id": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"num_prompts": 1000,
"duration": 97.65,
"completed": 1000,
"total_input_tokens": 215196,
"total_output_tokens": 43140,
"request_throughput": 10.24,
"input_throughput": 2203.64,
"output_throughput": 441.76,
"issue": "https://github.com/arc53/llm-price-compass/issues/6"
}

0 comments on commit 9404054

Please sign in to comment.