P3-LLM delivers 4.9x average speedup over HBM-PIM for edge LLM inference by pairing hybrid-format quantization with iso-area-optimized low-precision PIM compute units and operator fusion.
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats
P3-LLM delivers 4.9x average speedup over HBM-PIM for edge LLM inference by pairing hybrid-format quantization with iso-area-optimized low-precision PIM compute units and operator fusion.