↓Skip to main content
KAD

AI Inference

Alibaba XuanTie C950 RISC-V CPU: 5nm, 64 Cores and LLM Inference
·1261 words·6 mins
RISC-V XuanTie C950 Alibaba CPU Semiconductors AI Inference LLM Server Computing
Alibaba XuanTie C950 Runs 27B Qwen Model at 30 Tokens/s
·1677 words·8 mins
Alibaba XuanTie C950 RISC-V Qwen Edge AI AI Inference LLM AI Hardware
NVIDIA Rubin GPU Architecture: A Deep Technical Breakdown
·2196 words·11 mins
NVIDIA Rubin Vera Rubin Agentic-Ai GPU Architecture HBM4 NVLink AI Infrastructure AI Inference
AMD Instinct MI350P: 141GB HBM PCIe AI Accelerator Gains Momentum
·979 words·5 mins
AMD Instinct MI350P AI Accelerators CDNA 4 HBM PCIe Data Center AI Inference
Intel Arc Pro B70 Beats RTX 5090D in High-Concurrency AI Benchmark
·937 words·5 mins
Intel Arc Pro B70 AI Inference DeepSeek R1 GPU Benchmark FP16 Workstation GPU LLM Deployment
DSpark Explained: Semi-Autoregressive Speculative Decoding for Faster LLM Inference
·1357 words·7 mins
Large Language Models Speculative Decoding DeepSeek AI Inference Machine Learning Generative AI Transformer Models Inference Optimization
AWS Explores Qualcomm AI200 Chips with 768GB Memory for AI Inference
·572 words·3 mins
AWS Qualcomm AI200 AI Inference Cloud Computing Hyperscale AI Chips Data Center Hardware LLM Infrastructure Semiconductors
FuriosaAI and Broadcom Unveil 2nm AI Inference Accelerator
·1009 words·5 mins
AI FuriosaAI Broadcom AI Inference HBM4E GPU Data Center Semiconductor Accelerator LLM
Intel and SambaNova Redefine AI Inference Architecture in 2026
·638 words·3 mins
AI Inference Intel SambaNova Data Center LLM Hardware Architecture Edge AI
Reducing KV Cache Bottlenecks with NVIDIA Dynamo
·771 words·4 mins
NVIDIA AI Inference LLM GPU Storage