📄 文章列表

17 篇文章
AlphaSignal

Anthropic's Claude Now Flags Its Own Misuse at Under 2% Extra Cost

✅ completed ⭐ ☆☆☆☆☆ 2026-10-29
VentureBeat

Text handoffs slow AI models down. C2C lets them communicate through KV caches instead

✅ completed ⭐ ☆☆☆☆☆ 2026-09-22
VentureBeat

DeepSeek-V4.1-Flash debuts with $0.003/1M off-peak cached-input rate and benchmarks eclipsing GPT-5.6 Sol, Claude Opus 5

✅ completed ⭐ ☆☆☆☆☆ 2026-09-10
AlphaSignal

vLLM v0.23.0 Ships DeepSeek-V4 Production Hardening and 56% Throughput Boost | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-23
AlphaSignal

NVIDIA's LongLive-2.0 Generates 64-Second 720p Video Using 6x Less Memory | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
AlphaSignal

NVIDIA's DynoSim Screens Thousands of GPU Configs 1,500x Faster Than Real Time | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
AlphaSignal

Moonshot AI's Kimi K2.7 Code Hits 260 Tokens per Second on Agentic Coding | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
AlphaSignal

Moonshot AI's Kimi-K2.7-Code Beats Rivals With 30% Less Overthinking | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
AlphaSignal

Artificial Analysis' AA-AgentPerf Benchmark Exposes What AI Hardware Really Handles | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
TDS

Empowering LLMs to Think Deeper by Erasing Thoughts

✅ completed ⭐ ★★★★★★ 2025-05-12
TDS

Optimizing Token Generation in PyTorch Decoder Models

✅ completed ⭐ ★★★★★★ 2026-02-24
TDS

Why Care About Prompt Caching in LLMs?

✅ completed ⭐ ★★★★★★ 2026-03-13
TDS

Agentic AI: How to Save on Tokens

✅ completed ⭐ ★★★★★★ 2026-04-29
TDS

The Infrastructure Behind Making Local LLM Agents Actually Useful

✅ completed ⭐ ★★★★★★ 2026-05-28
TDS

Prefill Once, Fan Out: KV Snapshot Sharing for Multi-Agent LLM Pipelines

✅ completed ⭐ ★★★★★★ 2026-06-09
VentureBeat

Cheaper Tokens Bigger Bills The New Math Of Ai Infrastructure

✅ completed ⭐ ★★★★★★ 2026-06-23
VentureBeat

Googles New Turboquant Algorithm Speeds Up Ai Memory 8X Cutting Costs By 50

✅ completed ⭐ ★★★★★★ 2026-06-23