Kan Zhu

Spatiotemporal distribution of mixture homogeneity: Mechanism analysis of injection pulse width on combustion characteristics in hydrogen engines

Kan Zhu, Yunhua Zhang, Diming Lou, Liang Fang et autres

cn (code pays fourni par la source)

Investigation on the Influence of Injection Pulse Width on the Performance of a Hydrogen Internal Combustion Engine

Kan Zhu, Diming Lou, Yunhua Zhang, Liang Fang et autres

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba-Transformer architecture to provide best-in-class throughput and context lengths of up to …

NVIDIA Nemotron 3: Efficient and Open Intelligence

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We introduce the Nemotron 3 family of models - Nano, Super, and Ultra. These models deliver strong agentic, reasoning, and conversational capabilities. The Nemotron 3 family uses a Mixture-of-Experts hybrid Mamba-Transformer architecture to provide best-in-class throughput and context lengths of up to …

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on …

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman, Aaron Grattafiori et autres

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on …

Insight into combustion characteristic of a multi-point injection hydrogen engine from the view of hydrogen injection pulse width

Kan Zhu, Diming Lou, Yunhua Zhang, Liang Fang et autres

cn (code pays fourni par la source)

Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding

Yilong Zhao, Jiaming Tang, Kan Zhu, Zihao Ye et autres

Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation shifts the inference bottleneck from compute-bound to memory-bound. To generate each token, the model applies full attention to all previously generated tokens, …

Experimental investigation and multi-objective optimization of combustion characteristics and performance in a port-fuel-injected hydrogen engine

Xinyue Rao, Diming Lou, Yunhua Zhang, Zhiwei Wang et autres

cn (code pays fourni par la source)

PolyServe: Efficient Multi-SLO Serving at Scale

Kan Zhu, Haiyang Shi, Lei Xu, Jiaxin Shan et autres

Advances in Large Language Models (LLMs) have led to a surge of LLM-powered applications. These applications have diverse token-generation latency requirements. As a result, simply classifying workloads as latency-sensitive (LS) or best-effort (BE) overlooks the nuances within the latency-sensitive category and results …

Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs

Kan Zhu, Tian Tang, Qiang Xu, Yile Gu et autres

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full attention. However, these methods overlook variations in …

BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching

Yilong Zhao, Shuo Yang, Kan Zhu, Lianmin Zheng et autres

Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications. Meanwhile, recent progress in model capability and modality makes requests more diverse in compute and memory demands, creating …