Tagged "llm-inference"
- MediaTek Launches Dimensity 8550 4nm SoC with Integrated On-Device AI Focus
- Supercharging LLM Inference on Google TPUs: Achieving 3X Speedups With Diffusion-Style Speculative Decoding
- How to Make SSE Token Streams Resumable, Cancellable, and Multi-Device
- Unweight: Lossless MLP Weight Compression for LLM Inference
- Cutile.jl Brings Nvidia CUDA Tile-Based Programming to Julia
- AI Is Stress Testing Processor Architectures and RISC-V Fits the Moment