#GPU kernel tuning
156 related articles
·6 min
Tongyi Qianwen Qwen-Image-3.0: The Leap of AI Image Generation from Toy to Productivity Tool
Tongyi Qianwen Qwen-Image-3.0 image generation model gets a comprehensive upgrade: supporting 4,500-token ultra-long instructions, pixel-level detail rendering, 12-language knowledge understanding, and ancient painting restoration. This article analyzes its three core capabilities.
Read more →
Handwritten C/CUDA Inference Engine: P…
·2 min
Handwritten C/CUDA Inference Engine: Pushing Qwen 35B to the Limits on RTX 5090
A deep dive into a handwritten C/CUDA inference engine for Qwen 35B on RTX 5090 (Blackwell), covering quantization, FlashAttention kernels, and memory optimization.
Read more →
GitHub Daily · July 19: The Dual Advan…
·3 min
GitHub Daily · July 19: The Dual Advance of Heterogeneous Inference and Agent Toolchains
GitHub Trending July 19: ktransformers tops the list with heterogeneous inference optimization, while jcode, cua, and AstrBot signal a maturing Agent ecosystem.
Read more →
·4 min
The Local AI Inflection Point: Edge Deployment, Multi-Model Collaboration, and the Open-Source Ecosystem
AI Engineer Summit deep dive: Local AI hits a real inflection point, driven by privacy and cost. Multi-model collaboration goes mainstream, NVIDIA + ExoLabs achieve 10x gains, open-source ecosystem accelerates.
Read more →
Block Low-Rank Compression: A Guide to…
·2 min
Block Low-Rank Compression: A Guide to Accelerating Large Model Inference on Memory-Constrained GPUs
Learn how Block Low-Rank (BLR) decomposition compresses large model memory usage and accelerates GPU inference, including CUDA kernel optimization and combination with quantization and pruning.
Read more →
TurboVec: A Deep Dive into the Rust-Po…
·3 min
TurboVec: A Deep Dive into the Rust-Powered High-Performance Vector Index Library
TurboVec is a Rust-based vector index library powered by TurboQuant, with Python bindings for RAG, semantic search, and AI applications. A deep-dive into its architecture.
Read more →
·3 min
Complete Guide to Deploying LLMs Locally on RobotCore Mini: From Ollama Installation to Web Interface Setup
A complete guide to deploying LLMs locally on RobotCore Mini using Ollama — covering model pulling, CLI verification, Web backend setup, and LAN access.
Read more →
·3 min
GPUStack in Action: Complete Guide to Day 0 Deployment of DeepSeek-V4-Flash
Deploy DeepSeek-V4-Flash DSpark on 8× H20-141G using GPUStack's SGLang backend on Day 0. Full walkthrough of Web UI config, parameter tuning, and 200 tokens/sec benchmark results.
Read more →
4 Alternatives for Running CUDA on Non…
·3 min
4 Alternatives for Running CUDA on Non-NVIDIA Hardware: A Comparative Guide
A deep dive into running CUDA on non-NVIDIA hardware (AMD, Intel): comparing ROCm/HIP, ZLUDA, SYCL/oneAPI, and OpenCL across principles, use cases, and limitations.
Read more →
How NVIDIA BioNeMo Breaks Through Co-F…
·2 min
How NVIDIA BioNeMo Breaks Through Co-Folding End-to-End Performance Bottlenecks
How NVIDIA BioNeMo Agent Toolkit uses agent-based orchestration to solve MSA preprocessing, pipeline scheduling, and end-to-end bottlenecks in OpenFold3 co-folding workloads for drug discovery.
Read more →
Best Laptops for AI/ML Students: A Dee…
·2 min
Best Laptops for AI/ML Students: A Deep Dive Comparing Three Popular Models
Lenovo LOQ, HP Omen, or MacBook Air M5? A deep dive comparing GPU performance, RAM, and CUDA compatibility to help AI/ML students find the right laptop.
Read more →
·7 min
Breaking Down the Core Skills of an AI Application Engineer: From Beginner to Industrial-Grade Deployment
Knowing how to call an API doesn't make you an AI engineer. This article breaks down the complete skill structure of an AI application engineer, covering Python fundamentals, LLM fine-tuning, Agent development, and enterprise projects.
Read more →
·4 min
Unsloth Releases Qwen3.6 NVFP4 Quantization: 2.5x Faster with Zero Accuracy Loss
Unsloth releases NVFP4 quantization for Qwen3.6 using W4A4 true 4-bit Tensor Core computation, delivering up to 2.5x inference speedup over NVIDIA's official implementation with accuracy matching or exceeding BF16 on benchmarks like MMLU-Pro.
Read more →
·3 min
Benchmarking LLMs on Smartphones: A Deep Dive into the MELTing Point Benchmark
The MELTing Point paper is the first to evaluate mobile LLM performance in real user scenarios, covering iPhone, Samsung, Pixel and more, testing TinyLlama, Mistral-7B and others—revealing GPU inference gains, 47°C heat warnings, and prefill-decode disaggregation.
Read more →
·4 min
Testing a Research Automation Agent: Zero-Shot Reproduction of a NeurIPS Paper End-to-End
Testing research automation agent Klaus Goh: full reproduction of IBM's TTM time series paper at NeurIPS—from search to zero-shot inference, 2700+ predictions in 10 seconds, MSE 0.363 beating TimesFM.
Read more →
·5 min
From CNN to Transformer: How AI Evolved to Understand Human Language
From CNN and RNN to Transformer, a complete breakdown of the core evolution of AI natural language processing. Understand attention, BERT vs. GPT, and the architecture behind large models.
Read more →
·4 min
INT4 ConvRot W4A4 Quantization: Running Large Image Models on Low-VRAM GPUs in ComfyUI
An in-depth look at INT4 ConvRot W4A4 quantization, covering conversions of Krea2, Qwen-Image, and other diffusion models to help ComfyUI users run large image models on 8GB GPUs.
Read more →
·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 →
·7 min
Grok 4.5 Launch: Coding AI Market Reshuffle, Anthropic Claims Half the Territory
Grok 4.5 launches at just $0.49 per task, 90% cheaper than rivals. Anthropic's Claude Code claims 50% of the AI coding market. SambaNova raises $1B. Read the latest AI market shifts.
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 →