Anticancer platinum prodrugs that can be controllably activated are highly desired for personalized precision medicine and patient compliance in cancer therapy.However,the clinical application of platinum(Ⅳ)prodrugs(...Anticancer platinum prodrugs that can be controllably activated are highly desired for personalized precision medicine and patient compliance in cancer therapy.However,the clinical application of platinum(Ⅳ)prodrugs(Pt(Ⅳ))is restricted by tissue penetration of external irradiation.Here,we report a novel Pt(Ⅳ)activation strategy based on endogenous luminescence of tumor microenvironment responsiveness,which completely circumvents the limitation of external irradiation.The designed Pt(Ⅳ)–Lu,a mixture of trans,trans,trans-[Pt(N_(3))_(2)(OH)_(2)(py)_(2)]and luminol(Lu),has controllable activation property:it remains inert in reductant environment and normal tissues,but under tumor microenvironment,Lu will be oxidized to produce blue luminescence,which rapidly reduce Pt(Ⅳ)to Pt(Ⅱ)without the need of any external activator.Pt(Ⅳ)–Lu shows excellent responsive antitumor ability both in vitro and in vivo.Compared to cisplatin,the median lethal dose in BALB/c mice increased by an order of magnitude.Our results suggest that Pt(Ⅳ)–Lu exhibits highly controllable activation property,superior antitumor activity,and good biosafety,which may provide a novel strategy for the design of platinum prodrugs.展开更多
Large language models(LLMs)have exhibited remarkable performance across a broad spectrum of tasks,yet their extensive computational and memory requirements present substantial challenges for deployment in resource-con...Large language models(LLMs)have exhibited remarkable performance across a broad spectrum of tasks,yet their extensive computational and memory requirements present substantial challenges for deployment in resource-constrained scenarios.To address the challenges,this work introduces software and hardware co-optimization strategies aimed at enhancing the inference performance of LLMs on ARM CPU-based platforms.A mixed-precision quantization technique is employed,preserving the precision of critical weights to maintain model accuracy while quantizing non-essential weights to INT8,thereby reducing the model’s memory footprint.This work also capitalizes on the SIMD instruction set of ARM CPUs to efficiently process model data.Furthermore,the inference framework is optimized by fusing components of the attention computation and streamlining the dequantization process through modifications to the scaling factor.These enhancements result in a significant reduction in model memory usage and improved throughput during the prefill and decode stages.The efficacy of the proposed approach is demonstrated through the optimization of the Qwen-1.8B model on Armv9,with only a 0.66%decrease in accuracy and a reduction in memory usage to 58.8%of the baseline,while achieving a 4.09×and 15.23×increase in inference performance for the prefill and decode stages over the baseline,respectively.展开更多
基金supported by the National Natural Science Foundation of China(Nos.32201171 and 82372115)the Science and Technology Program of Guangzhou(No.202102021266)。
文摘Anticancer platinum prodrugs that can be controllably activated are highly desired for personalized precision medicine and patient compliance in cancer therapy.However,the clinical application of platinum(Ⅳ)prodrugs(Pt(Ⅳ))is restricted by tissue penetration of external irradiation.Here,we report a novel Pt(Ⅳ)activation strategy based on endogenous luminescence of tumor microenvironment responsiveness,which completely circumvents the limitation of external irradiation.The designed Pt(Ⅳ)–Lu,a mixture of trans,trans,trans-[Pt(N_(3))_(2)(OH)_(2)(py)_(2)]and luminol(Lu),has controllable activation property:it remains inert in reductant environment and normal tissues,but under tumor microenvironment,Lu will be oxidized to produce blue luminescence,which rapidly reduce Pt(Ⅳ)to Pt(Ⅱ)without the need of any external activator.Pt(Ⅳ)–Lu shows excellent responsive antitumor ability both in vitro and in vivo.Compared to cisplatin,the median lethal dose in BALB/c mice increased by an order of magnitude.Our results suggest that Pt(Ⅳ)–Lu exhibits highly controllable activation property,superior antitumor activity,and good biosafety,which may provide a novel strategy for the design of platinum prodrugs.
基金the National Key Research and Development Program of China under Grant 2023YFB2806000the Postdoctoral Fellowship Program of CPSF under Grant GZC20241305the Proof of Concept Foundation of Xidian,University Hangzhou Institute of Technology,under Grant GNYZ2024JC004.
文摘Large language models(LLMs)have exhibited remarkable performance across a broad spectrum of tasks,yet their extensive computational and memory requirements present substantial challenges for deployment in resource-constrained scenarios.To address the challenges,this work introduces software and hardware co-optimization strategies aimed at enhancing the inference performance of LLMs on ARM CPU-based platforms.A mixed-precision quantization technique is employed,preserving the precision of critical weights to maintain model accuracy while quantizing non-essential weights to INT8,thereby reducing the model’s memory footprint.This work also capitalizes on the SIMD instruction set of ARM CPUs to efficiently process model data.Furthermore,the inference framework is optimized by fusing components of the attention computation and streamlining the dequantization process through modifications to the scaling factor.These enhancements result in a significant reduction in model memory usage and improved throughput during the prefill and decode stages.The efficacy of the proposed approach is demonstrated through the optimization of the Qwen-1.8B model on Armv9,with only a 0.66%decrease in accuracy and a reduction in memory usage to 58.8%of the baseline,while achieving a 4.09×and 15.23×increase in inference performance for the prefill and decode stages over the baseline,respectively.
