📄 文章列表
448 篇文章
AlphaSignal
AMD and Cerebras Pair Helios With Wafer-Scale Engine for 5x Faster Inference | AlphaSignal
AlphaSignal
Cursor's AI Swarm Rebuilt SQLite From Scratch at 15x Lower Cost | AlphaSignal
TDS
One RAG Pipeline, Four Very Different PDFs: Same Four Bricks, Every Answer Typed and Cited
TDS
Don’t Let Claude Grade Its Own Homework
AlphaSignal
vLLM's TileRT Integration Hits 618 tok/s by Splitting AI's Two Hardest Jobs | AlphaSignal
AlphaSignal
Alibaba's Qwen-Audio-3.0-TTS-Plus Tops Global Speech Arena With Elo 1,236 | AlphaSignal
TDS
How Much Does It Actually Cost to Run a Local LLM? (Euros per Million Tokens, Measured)
AlphaSignal
Cerebras Runs Gemma 4 31B at 35x GPU Speed on Its Cloud | AlphaSignal
AlphaSignal
vLLM-Omni Squeezes 172% More Audio Out of Four Speech Models | AlphaSignal
AlphaSignal
Unsloth's Qwen3.6 NVFP4 Hits 17,561 Tokens per Second on a Single GPU | AlphaSignal
AlphaSignal
Together AI's ParallelKernelBench Reveals Frontier Models Struggle Across Multi-GPU Clusters | AlphaSignal
AlphaSignal
OpenAI's GPT-5.4 Runs 10,080 Drug Reactions to Crack a Decades-Old Chemistry Problem | AlphaSignal
AlphaSignal
Inception Labs' Mercury 2 Hits 1,000 Tokens per Second on Azure | AlphaSignal
AlphaSignal
humans& Open-Sources the First Stable 4-Bit RL Training Recipe at 1.73x Speedup | AlphaSignal
AlphaSignal
Google DeepMind Ships Gemini Omni Flash to Turn Images Into Editable Videos | AlphaSignal
AlphaSignal
DeepSeek's DSpark Makes DeepSeek-V4 Generation 85% Faster at Any Scale | AlphaSignal
AlphaSignal
Cursor 3.11 Lets Developers Run Parallel AI Chats Without Stopping Their Agent | AlphaSignal
AlphaSignal
Ant Group Pushes Qwen3-Omni to 5.4x Faster With 0.6s Audio Response | AlphaSignal
AlphaSignal
Moonshot AI's Kimi K2.7 Code HighSpeed Hits 260 Tokens per Second | AlphaSignal
AlphaSignal