Large Language Model Inference on Code Assistant
104TPSDReSD
Evaluation Results
| Method | Links | |
|---|---|---|
| DReSDBackbone=CodeLlama-7B, Decoding Strategy=greedy decoding2025.02 | 104 | |
| DReSDBackbone=CodeLlama-13B, Decoding Strategy=greedy decoding2025.02 | 85 | |
| DReSDBackbone=Llama2-Chat-7B, Decoding Strategy=greedy decoding2025.02 | 78 | |
| RESTBackbone=CodeLlama-7B, Decoding Strategy=greedy decoding2025.02 | 72 | |
| RESTBackbone=Llama2-Chat-7B, Decoding Strategy=greedy decoding2025.02 | 55 | |
| DReSDBackbone=Llama2-Chat-13B, Decoding Strategy=greedy decoding2025.02 | 50 | |
| PLDBackbone=CodeLlama-7B, Decoding Strategy=greedy decoding2025.02 | 42 | |
| RESTBackbone=CodeLlama-13B, Decoding Strategy=greedy decoding2025.02 | 39 | |
| RESTBackbone=Llama2-Chat-13B, Decoding Strategy=greedy decoding2025.02 | 32 | |
| SDBackbone=CodeLlama-7B, Decoding Strategy=greedy decoding2025.02 | 31 | |
| PLDBackbone=CodeLlama-13B, Decoding Strategy=greedy decoding2025.02 | 29 | |
| SDBackbone=Llama2-Chat-7B, Decoding Strategy=greedy decoding2025.02 | 25 | |
| SDBackbone=CodeLlama-13B, Decoding Strategy=greedy decoding2025.02 | 21 | |
| PLDBackbone=Llama2-Chat-7B, Decoding Strategy=greedy decoding2025.02 | 21 | |
| SDBackbone=Llama2-Chat-13B, Decoding Strategy=greedy decoding2025.02 | 20 | |
| LLMBackbone=CodeLlama-7B, Decoding Strategy=greedy decoding2025.02 | 19 | |
| LLMBackbone=Llama2-Chat-7B, Decoding Strategy=greedy decoding2025.02 | 19 | |
| PLDBackbone=Llama2-Chat-13B, Decoding Strategy=greedy decoding2025.02 | 19 | |
| LLMBackbone=CodeLlama-13B, Decoding Strategy=greedy decoding2025.02 | 15 | |
| LLMBackbone=Llama2-Chat-13B, Decoding Strategy=greedy decoding2025.02 | 15 |