Trending

Show HN: Maestro – A Framework to Orchestrate and Ground Competing AI Models

Does Field Ordering Affect Model Performance?

LLM function calls don't scale; code orchestration is simpler, more effective

LLM-D: Kubernetes-Native Distributed Inference at Scale

llm-d, Kubernetes native distributed inference

Publisher: The Malloy Semantic Model Server

Ash Framework – Model your domain, derive the rest

Is there a balance to be struck between simple hierarchical models and

Show HN: OpenRouter Model Price Comparison

[D] Implementing GPU snapshotting to cut cold starts for large models by 12x

Any framework for Eval?

Chinese models pulling away

[P] Fine-tuning a fast, local “tab tab” code completion model for Marimo notebooks

Agent Builder: Your preferred framework/library vs pybotchi

[D] Why CDF normalization is not used in ML? Leads to more uniform distributions - better for generalization

Has anyone nailed SDR Agent

[D] How to improve pretraining pipeline

[D] Review Confidence Guidelines

microsoft

Save item

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

aws

Save item

amazon-sagemaker-examples

Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.

Deci-AI

Save item

super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

huggingface

Save item

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

modelscope

Save item

modelscope

ModelScope: bring the notion of Model-as-a-Service to life.