📄 文章列表
32 篇文章
AlphaSignal
Baidu's ERNIE Evolve Rewrites Its Own AI Code and Boosts Speed 6x
AlphaSignal
Sarvam's Prism Turns a 105B Open Model Into a 44ms Decision Engine
AlphaSignal
Humans& Ships Weight Teleportation to Sync 445 GB AI Models in 220 ms
AlphaSignal
NVIDIA's RE-USE Beats 500M-Parameter Models at Cleaning Speech With Just 9.6M
TDS
Three Samplers, One Posterior: NUTS vs. Emcee vs. Nested Sampling
TDS
AI Agents Beat PyTorch: Writing Faster CUDA Kernels
TDS
Your LLM Has a Curved Space of Paragraphs
VentureBeat
Enterprises put non-Nvidia chips 14 points ahead of Nvidia's next-gen GPUs on their evaluation lists
TDS
How a Frontier Model Gets Built, Read from the Kimi K3 Report
AlphaSignal
Moonshot AI Open-Sources FlashKDA, Making Kimi Linear 2x Faster on GPUs | AlphaSignal
AlphaSignal
Unsloth Ships AMD GPU Support, Bringing 2x Faster Fine-Tuning to Radeon | AlphaSignal
AlphaSignal
PyTorch's Triton 3.7 Lets Developers Load Custom GPU Compilers Without Forking | AlphaSignal
AlphaSignal
vLLM v0.22.0 Ships a Rust Frontend and Cuts Latency by 28.9% | AlphaSignal
AlphaSignal
vLLM's Rust Frontend Beats 32 Python Processes With a Single One | AlphaSignal
AlphaSignal
Google Launches TPU Developer Hub to Finally Make TPUs as Easy as GPUs | AlphaSignal
AlphaSignal
Alibaba's Qwen3.7-Max Runs 35 Hours Straight to Hit a 10x Coding Speedup | AlphaSignal
TDS
The Hot Path Belongs to GBDTs, Agents Own the Cold Path: A Payment-Fraud Benchmark
TDS
Maximizing AI/ML Model Performance with PyTorch Compilation
TDS
Learning Triton One Kernel At a Time: Vector Addition
TDS
Learning Triton One Kernel at a Time: Matrix Multiplication
1
2