📄 文章列表

5 篇文章

TDS

Prefill Is Compute-Bound. Decode Is Memory-Bound. Why Your GPU Shouldn’t Do Both.

✅ completed ⭐ ★★★★★★ 2026-04-15

TDS

6 Things I Learned Building LLMs From Scratch That No Tutorial Teaches You

✅ completed ⭐ ★★★★★★ 2026-04-17

TDS

How a 2021 Quantization Algorithm Quietly Outperforms Its 2026 Successor

✅ completed ⭐ ★★★★★★ 2026-05-02

TDS

The Must-Know Topics for an LLM Engineer

✅ completed ⭐ ★★★★★★ 2026-05-09

VentureBeat

The Team Behind Continuous Batching Says Your Idle Gpus Should Be Running

✅ completed ⭐ ★★★★★★ 2026-06-23