📄 文章列表

25 篇文章
AlphaSignal

Sarvam's Prism Turns a 105B Open Model Into a 44ms Decision Engine

✅ completed ⭐ ☆☆☆☆☆ 2026-11-03
cn_ai

模拟计算进入矩阵时代！北大联手硅谷IBM，写下新定义

✅ completed ⭐ ☆☆☆☆☆ 2026-11-03
AlphaSignal

NVIDIA's RE-USE Beats 500M-Parameter Models at Cleaning Speech With Just 9.6M

✅ completed ⭐ ☆☆☆☆☆ 2026-10-30
AlphaSignal

Pika Labs Releases Pika H3 Flex to Generate 15-Second Videos in 7 Seconds

✅ completed ⭐ ☆☆☆☆☆ 2026-10-31
cn_ai

世界模型首次指导设计芯片！超大核NPU700TOPS，99%算力可用

✅ completed ⭐ ☆☆☆☆☆ 2026-10-31
TDS

The Number Your Quantization Gate Doesn't Have

✅ completed ⭐ ☆☆☆☆☆ 2026-10-18
TDS

Why Temperature 0 Isn't Deterministic

✅ completed ⭐ ☆☆☆☆☆ 2026-10-10
TDS

AI Agents Beat PyTorch: Writing Faster CUDA Kernels

✅ completed ⭐ ☆☆☆☆☆ 2026-10-10
TDS

How To Build Your Own LLM Runtime From Scratch

✅ completed ⭐ ☆☆☆☆☆ 2026-07-22
AlphaSignal

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

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
TDS

Behind the Scenes of Distributed Training and Why Your GPU Wiring Matters as Much as Your Strategy

✅ completed ⭐ ☆☆☆☆☆ 2026-07-09
TDS

Persistent Latent Memory for Multi-Hop LLM Agents: How a 6G Handover Paper Closes the Agent Cold-Start

✅ completed ⭐ ☆☆☆☆☆ 2026-07-01
AlphaSignal

NVIDIA's NVFP4 Makes Llama 3.1 405B Train 1.73x Faster on Blackwell | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
TDS

Model Compression: Make Your Machine Learning Models Lighter and Faster

✅ completed ⭐ ★★★★★★ 2025-05-08
TDS

Boost 2-Bit LLM Accuracy with EoRA

✅ completed ⭐ ★★★★★★ 2025-05-15
TDS

I Made My AI Model 84% Smaller and It Got Better, Not Worse

✅ completed ⭐ ★★★★★★ 2025-09-29
TDS

What Happens When You Build an LLM Using Only 1s and 0s

✅ completed ⭐ ★★★★★★ 2025-12-22
TDS

Breaking the Hardware Barrier: Software FP8 for Older GPUs

✅ completed ⭐ ★★★★★★ 2025-12-28
TDS

Optimizing Data Transfer in Distributed AI/ML Training Workloads

✅ completed ⭐ ★★★★★★ 2026-01-23
TDS

AI in Multiple GPUs: ZeRO & FSDP

✅ completed ⭐ ★★★★★★ 2026-03-05