5 papers
HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction
Luxi Lin, Shuang Peng, Rui Ma +7
We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC). Despite the strong performance of DeepSeek-V4's native Mul…
Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
Zhangying Feng, Qianglong Chen, Ning Lu +6
The development of reasoning capabilities represents a critical frontier in large language models (LLMs) research, where reinforcement learning (RL) and process reward models (PRMs…
EdgeInfinite-Instruct: Bridging SFT-Based Optimization and NPU-Level Efficiency for Edge Devices
Jiyu Chen, Poh Seng Lim, Shuang Peng +12
Deploying Transformer-based large language models (LLMs) on resource-constrained edge devices for long-sequence tasks remains challenging due to the quadratic time complexity of se…
BlueLM-2.5-3B Technical Report
Baojiao Xiong, Boheng Chen, Chengzhi Wang +58
We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reas…
EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
Jiyu Chen, Shuang Peng, Daxiong Luo +4
Transformer-based large language models (LLMs) encounter challenges in processing long sequences on edge devices due to the quadratic complexity of attention mechanisms and growing…