Follow
Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms https://arxiv.org/abs/2511.19438 #cs.DC #cs.PF
Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms https://arxiv.org/abs/2511.19438 #cs.DC #cs.PF