📄 文章列表
37 篇文章
AlphaSignal
Baidu's ERNIE Evolve Rewrites Its Own AI Code and Boosts Speed 6x
AlphaSignal
Epoch's IPI Shows Nvidia GB300 Delivers 25x an H100's Real Inference Capacity
AlphaSignal
Software Tuning Boosts DeepSeek V4.1 Flash Throughput 60% on Unchanged NVIDIA Hardware
AlphaSignal
Together AI's Compiler Uses Agents to Speed Up GPU Inference by 20%
AlphaSignal
Artificial Analysis Finds 1 in 4 AI Endpoints Quietly Underperform Their Advertised Models
AlphaSignal
Unsloth Shrinks Qwen3.8-Flash-Next to 74.5 GB for Local Coding Agents
AlphaSignal
Baidu Drops ERNIE 5.5 Flash, a Raw 280B Open Checkpoint Beating DeepSeek
AlphaSignal
SGLang's HiCache Slashes AI Response Times by 60% Across Distributed Clusters
TDS
Speculative Decoding on CPUs: Nearly 4x Faster Token Generation with DFlash
AlphaSignal
PrismML Shrinks Bonsai 27B to 3.9 GB so It Runs on an iPhone | AlphaSignal
AlphaSignal
DeepSeek's DSpark Makes DeepSeek-V4 Generation 85% Faster at Any Scale | AlphaSignal
VentureBeat
DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%
AlphaSignal
Top Agentic Performance, Low Cost: GLM-5.2, designed for coding and long-running agentic jobs, now the top open model
AlphaSignal
How Anthropic aligns its models: OpenAI improves realtime audio capabilities
AlphaSignal
A New Generation Studies AI, Apple's Recipe for On-Device Models, GLM5.2 Tackles Open-Ended Problems
AlphaSignal
StepFun's Step 3.7 Flash Hits 416 Tokens per Second While Staying Open-Source | AlphaSignal
AlphaSignal
NVIDIA Shrinks GLM-5.2 Memory by 1.8x With NVFP4 Without Losing Accuracy | AlphaSignal
AlphaSignal
NVIDIA's Nemotron 3 Ultra Hits 6x Faster Inference With 550B Open Model | AlphaSignal
AlphaSignal
Google DeepMind's DiffusionGemma Generates Text 4x Faster by Ditching Tokens | AlphaSignal
AlphaSignal
Google Boosts Gemini Nano on Pixel 50% Faster Without Retraining | AlphaSignal
1
2