📄 文章列表

46 篇文章
TDS

The Hidden Cost of LLM Routing: Why Switching Models Costs More

✅ completed ⭐ ☆☆☆☆☆ 2026-10-20
VentureBeat

Meta unveils Muse Spark Open, the new top U.S. open weights model — and it runs on two paired Mac desktops

✅ completed ⭐ ☆☆☆☆☆ 2026-10-15
VentureBeat

Black Forest Labs opens FLUX 3 Image Klein weights, with free commercial use limited to smaller businesses

✅ completed ⭐ ☆☆☆☆☆ 2026-10-15
TDS

The KV Cache Tax: Why Inference Servers Run Out of Memory Before Compute

✅ completed ⭐ ☆☆☆☆☆ 2026-09-16
TDS

Disaggregation Is a Thousand-GPU Problem

✅ completed ⭐ ☆☆☆☆☆ 2026-09-05
VentureBeat

Qwen3.8-27B runs frontier-class coding agents and reasoning locally, no cloud API required

✅ completed ⭐ ☆☆☆☆☆ 2026-08-18
AlphaSignal

vLLM's TileRT Integration Hits 618 tok/s by Splitting AI's Two Hardest Jobs | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-14
AlphaSignal

Unsloth's Qwen3.6 NVFP4 Hits 17,561 Tokens per Second on a Single GPU | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

DeepSeek's DSpark Makes DeepSeek-V4 Generation 85% Faster at Any Scale | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

Thinking Machines debuts a new type of model: Google’s AI mouse promises better human-AI interaction

✅ completed ⭐ ★★★★★ 2026-05-13
AlphaSignal

Anthropic’s Claude Mythos Problem, Dark DNA Unveiled, Pitfalls for Assistive Models, Simulating Fluid Dynamics

✅ completed ⭐ ★★★★★ 2026-04-10
Rundown.AI

China is coming for Tesla Optimus

✅ completed ⭐ ★★★★★★ 2024-08-26
AlphaSignal

vLLM Launches vime to Fix RL Fine-Tuning's Worst Numerical Drift Problem | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26
AlphaSignal

StepFun's Step 3.7 Flash Hits 416 Tokens per Second While Staying Open-Source | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26
AlphaSignal

NVIDIA Backs DFlash to Boost LLM Inference 15x on Blackwell | AlphaSignal

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

Z Lab's DFlash Hits 4.3x Throughput by Drafting Tokens in Parallel | AlphaSignal

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

vLLM Launches vime to Fix RL Fine-Tuning's Worst Numerical Drift Problem | AlphaSignal

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

StepFun's Step 3.7 Flash Hits 416 Tokens per Second While Staying Open-Source | AlphaSignal

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

SGLang Breaks 12,000 Tokens per Second on DeepSeek V4 Pro | AlphaSignal

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

EAGLE 3.1 Fixes a Silent Bug Making AI Inference 2x Faster in Production | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27