#CUDA programming
163 related articles
·5 min
Getting Started with LangChain: LLM Invocation, Agent Practice, and Environment Setup Guide
Starting from the three limitations of LLMs, this guide systematically explains LangChain's core positioning, environment setup, API key prep, model init, and the message system. Learn init_chat_model and AIMessage/HumanMessage/SystemMessage.
Read more →
·2 min
AI Agents for SGLang Kernel Optimization: Real-World Performance Gains and Engineering Methodology
SGLang's team converted expert knowledge into agent skills, achieving 71.4% throughput gains, TTFT reduced from 456ms to 168ms. A deep dive into agent-assisted kernel optimization methodology.
Read more →
·3 min
ComfyUI-INT4-Fast: Running Flux Models Smoothly on 6GB GPUs
ComfyUI-INT4-Fast brings W4A4 quantized inference to ComfyUI. RTX 3060 (6GB VRAM) generates 1024×1024 images in 17s. Per-layer mixed-precision routing balances speed and quality for Flux models.
Read more →
·6 min
AI's Second Half: The Decisive Battle Shifts from Models to Infrastructure
Model capabilities are converging, making inference cost and scalability the new focus of AI competition. A deep analysis of AI infrastructure's core layers.
Read more →
·2 min
GLM-5.2 Spotted in Testing | Claude Fable 5 Launches: 4 Key AI Updates
GLM-5.2 spotted in testing, Anthropic launches Claude Fable 5, Moore Threads open-sources MusaCoder for domestic GPUs, and Google releases Gemini real-time translation.
Read more →
·5 min
TensorRT Multi-Device Inference: Engineering Practices for Breaking Through Single-GPU Memory Bottlenecks
NVIDIA TensorRT now supports multi-device inference via pipeline and tensor parallelism, distributing large models across multiple GPUs to break through single-card memory limits.
Read more →
·7 min
Reverse-Engineering CUDA-checkpoint: The Technical Principles and Practice of Cracking GPU Cold Starts
An in-depth analysis of reverse-engineering Nvidia CUDA-checkpoint to accelerate GPU cold starts. Covers checkpoint/restore, Serverless GPU prospects, and VRAM snapshot challenges.
Read more →
·7 min
Getting Started with LangChain 1.3: Core Concepts of LLMs and Agents
An in-depth breakdown of LangChain 1.3's core concepts, covering the three major limitations of LLMs, Agent architecture, memory management, and a complete learning path. Master LangChain and LangGraph to quickly build AI development skills.
Read more →
·2 min
Unsloth v0.1.462-beta: Keyboard Navigation and Accessibility Improvements for Model Picker
Unsloth v0.1.462-beta adds full keyboard navigation to the Studio Model Picker, fixes Tab focus order, and improves accessibility for LLM fine-tuning workflows.
Read more →
·4 min
AI Weekly: GPT-5.6 Launches in Three Tiers, Open-Source Inference Frameworks and Robot Safety Break Through Across the Board
This week in AI: OpenAI launches GPT-5.6 in three tiers (Sol/Terra/Luna) hitting 91.9% on coding benchmarks; DeepSeek and PKU open-source DSpark for 85% faster inference; Prime Intellect trains trillion-param models on just 28 H200s; Anthropic Claude enters Slack.
Read more →
·4 min
Unsloth v0.1.463-beta: Fixes Studio Crash and llama-server Permission Issue
Unsloth v0.1.463-beta fixes a Studio crash caused by access-denied errors during llama-server service discovery. Improves stability for multi-user servers and Windows environments.
Read more →
·6 min
AMD Ryzen AI Halo Dev Kit: A $4,000 Local LLM Powerhouse Taking on Apple and NVIDIA
AMD officially unveils the Ryzen AI Halo local AI dev kit, priced around $4,000 with 128GB unified memory, capable of running 70B LLMs locally. An in-depth look at its specs, pricing, and market competition.
Read more →
·5 min
DeepSeek DSpec Hands-On: How Speculative Decoding Accelerates LLM Inference by 6x
Hands-on report on DeepSeek's open-source inference acceleration toolkit DSpec: draft model + smart scheduling delivers lossless speedup, hitting acceptance length 6 on GSM8K and reproducing official data.
Read more →
·4 min
Claude Science Launch: Anthropic's AI Assistant Built for End-to-End Scientific Research
Anthropic launches Claude Science (beta), a research-focused AI app with artifact traceability, on-demand environments, and 60+ scientific database integrations.
Read more →
·6 min
AI for Beginners: A Five-Step Practical Path That Skips the Math and Python Syntax Traps
Struggling with math and Python when learning AI from scratch? This article lays out a five-step entry path: grasp the concepts, learn Python lightly, master ML and deep learning principles, get hands-on with PyTorch, then deepen understanding through real projects.
Read more →
·5 min
Python Learning Roadmap for Beginners: A Three-Stage System to Avoid 90% of Detours
Learning Python from scratch? This article breaks down the three learning stages—Fundamentals, Intermediate, and Practice—covering variables, OOP, scraping, and data analysis to help you plan a systematic Python path.
Read more →
·5 min
Major Unsloth Update: NVFP4 Quantization Export and DeepSeek-V4 Training Support
Unsloth v0.1.48-beta released, adding NVFP4/FP8 quantization export, OpenAI-compatible API hot-swapping, 3-5x faster MoE training, and 1.3x faster GRPO, covering the full LLM fine-tuning, quantization, and local deployment pipeline.
Read more →
·2 min
PyTorch Hits 100K Stars: Unpacking the Dominance of the Leading Deep Learning Framework
PyTorch hits 100K GitHub stars, cementing its status as the leading deep learning framework. Explore why developers love PyTorch's dynamic graphs, GPU acceleration, and ecosystem.
Read more →
·6 min
Deep Dive into GPT-5.6 Ultra's Sub-Agent Architecture and Ten Key AI Industry Trends
In-depth analysis of GPT-5.6 Ultra's sub-agent collaborative reasoning, the global rise of Chinese AI models, world-model evaluation gaps, and AI's real-world deployment challenges and bubble warnings.
Read more →
·2 min
Unsloth v0.1.461-beta: Fix for Local GGUF Vision Model Loading
Unsloth v0.1.461-beta fixes local GGUF vision model loading on llama-server in Studio, adds variant directory companion file lookup for stable multimodal deployment.
Read more →