An exploit-heavy multi-agent LLM system with error-fixing agents delivers 2.88x average speedup over PyTorch Eager and 1.85x over torch.compile on H100 GPUs across KernelBench tasks.
ISBN 9798331314385
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems
An exploit-heavy multi-agent LLM system with error-fixing agents delivers 2.88x average speedup over PyTorch Eager and 1.85x over torch.compile on H100 GPUs across KernelBench tasks.