AI 知识库 | 文章列表

AlphaSignal

Unsloth Shrinks Qwen3.8-Flash-Next to 74.5 GB for Local Coding Agents

✅ completed ⭐ ☆☆☆☆☆ 2026-11-04

cn_ai

英伟达团队基于 MiniMax H3 开源视频增强方案，最高支持 4K 重生成

✅ completed ⭐ ☆☆☆☆☆ 2026-10-30

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

TDS

How GRPO Trains Small Language Models with Verifiable Rewards

✅ completed ⭐ ☆☆☆☆☆ 2026-09-24

TDS

How to Fine-Tune an LLM: An End-to-End Guide

✅ completed ⭐ ☆☆☆☆☆ 2026-08-20

TDS

Building Multimodal Workflows with a Local LLM

✅ completed ⭐ ☆☆☆☆☆ 2026-08-12

AlphaSignal

Unsloth Ships AMD GPU Support, Bringing 2x Faster Fine-Tuning to Radeon | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-20

AlphaSignal

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

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12

AlphaSignal

Hugging Face's OpenEnv Gives Open-Source Developers a Shared RL Training Standard | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26

AlphaSignal

Hugging Face's OpenEnv Gives Open-Source Developers a Shared RL Training Standard | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27

AlphaSignal

Google Shrinks Gemma 4 to 1GB so It Runs on Your Phone | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27

TDS

How to Benchmark DeepSeek-R1 Distilled Models on GPQA Using Ollama and OpenAI’s simple-evals

✅ completed ⭐ ★★★★★★ 2025-04-23

TDS

Fine-Tuning VLMs for Document Understanding

✅ completed ⭐ ★★★★★★ 2025-05-05

TDS

How I Fine-Tuned Granite-Vision 2B to Beat a 90B Model — Insights and Lessons Learned

✅ completed ⭐ ★★★★★★ 2025-07-25

TDS

Learning Triton One Kernel At a Time: Vector Addition

✅ completed ⭐ ★★★★★★ 2025-09-27

TDS

Learning Triton One Kernel at a Time: Softmax

✅ completed ⭐ ★★★★★★ 2025-11-23

TDS

Cutting LLM Memory by 84%: A Deep Dive into Fused Kernels

✅ completed ⭐ ★★★★★★ 2026-01-16

TDS

Self-Hosting Your First LLM

✅ completed ⭐ ★★★★★★ 2026-03-17

TDS

How to Fine-Tune an SLM for Emotion Recognition

✅ completed ⭐ ★★★★★★ 2026-06-05

TDS

Run a Local LLM with OpenClaw on Your Mac Mini

✅ completed ⭐ ★★★★★★ 2026-06-16

📄 文章列表

Unsloth Shrinks Qwen3.8-Flash-Next to 74.5 GB for Local Coding Agents

英伟达团队基于 MiniMax H3 开源视频增强方案，最高支持 4K 重生成

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

How GRPO Trains Small Language Models with Verifiable Rewards

How to Fine-Tune an LLM: An End-to-End Guide

Building Multimodal Workflows with a Local LLM

Unsloth Ships AMD GPU Support, Bringing 2x Faster Fine-Tuning to Radeon | AlphaSignal

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

Hugging Face's OpenEnv Gives Open-Source Developers a Shared RL Training Standard | AlphaSignal

Hugging Face's OpenEnv Gives Open-Source Developers a Shared RL Training Standard | AlphaSignal

Google Shrinks Gemma 4 to 1GB so It Runs on Your Phone | AlphaSignal

How to Benchmark DeepSeek-R1 Distilled Models on GPQA Using Ollama and OpenAI’s simple-evals

Fine-Tuning VLMs for Document Understanding

How I Fine-Tuned Granite-Vision 2B to Beat a 90B Model — Insights and Lessons Learned

Learning Triton One Kernel At a Time: Vector Addition

Learning Triton One Kernel at a Time: Softmax

Cutting LLM Memory by 84%: A Deep Dive into Fused Kernels

Self-Hosting Your First LLM

How to Fine-Tune an SLM for Emotion Recognition

Run a Local LLM with OpenClaw on Your Mac Mini