Catalogue

Tool

NeMo

VoiceGenerative MediaTraining

NVIDIA

NVIDIA framework for building speech AI models, including ASR, TTS, translation, and speaker diarization

sttttsdiarizationtranslation

Tool

Ray

InferenceTrainingDeployment

ray-project

Distributed runtime and ML libraries for scaling Python and AI workloads from a laptop to a cluster

distributed-computingreinforcement-learninghyperparameter-tuning

Tool

Axolotl

Training

OpenAccess-AI-Collective

Open-source framework for fine-tuning and post-training large language models across many architectures and hardware setups

fine-tuneloramoequantization

Framework

DSPy

CodingTraining

stanfordnlp

Compose LM pipelines as declarative Python modules, then optimize their prompts and weights algorithmically

promptragself-improvement

Tool

OpenJarvis

InferenceTraining

open-jarvis

Personal AI, On Personal Devices

productivitylocal-firstollamaclicron

Tool

LlamaFactory

Training

hiyouga

Fine-tune and post-train open LLMs across many families through a command line or Gradio web UI, with no training code required

fine-tunelorareinforcement-learninggui

Tool

Unsloth

TrainingInference

unslothai

Run and fine-tune open LLMs, vision, and audio models locally, with training claimed at up to 2x faster and up to 70% less VRAM

fine-tuneloragguflocal-first

Tool

Wandb

MonitoringTraining

wandb

Tracks and visualizes machine learning experiments and models, with framework integrations and cloud or self-hosted deployment

experiment-trackingmlopshyperparameter-tuningmodel-versioning

Tool

Diffusers

Generative MediaInferenceTraining

huggingface

Library of pretrained diffusion models for generating images, audio, and 3D structures, for inference or training

diffusionstable-diffusionpytorchflux

Tool

KTransformers

InferenceTraining

kvcache-ai

Framework for LLM inference and fine-tuning on CPU-GPU heterogeneous hardware, tuned for large mixture-of-experts models

moecpu-gpufine-tune

Tool

Soup

Training

MakazhanAlpamys

Fine-tuning a small model on a few hundred rows costs a fraction of sending the same task through an API.

loradpoquantizationconsumer-gpu

Tool

RLinf

Training

RLinf

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

reinforcement-learningdistributed-trainingroboticsfine-tune

Tool

rLLM

TrainingQA

rllm-org

rLLM bolts RL onto agents you already wrote. verl, trlx, OpenRLHF make you rewrite the agent into their pipeline. A deco

reinforcement-learningagent-trainingsandboxdistributed-training

Framework

ART (Agent Reinforcement Trainer)

Training

OpenPipe

Open-source GRPO reinforcement-learning trainer for multi-step LLM agents

reinforcement-learninggrpofine-tunelora

Tool

Surogate

TrainingDeployment

invergent-ai

Fine-tuning a small model on a few hundred rows costs a fraction of sending the same task through an API. Soup runs that

fine-tunegrpodpolora

Tool

TuFT

TrainingDeployment

agentscope-ai

Multi-tenant fine-tuning for LLMs with Tinker-compatible API

fine-tunemulti-tenantgpusdk

Tool

Miles

Training

radixark

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

reinforcement-learningfine-tunevision-language-modeldistributed-training

Platform

Together AI

InferenceTrainingDeployment

togethercomputer

Inference, fine-tuning and GPU-cluster platform serving open-weight models.

gpu-clusterfine-tuneapisdk

Tool

Mergekit

Training

arcee-ai

Toolkit for merging pretrained language models out-of-core, including evolutionary merge methods

model-mergingmixture-of-expertslorafine-tune

Tool

Inworld

VoiceGenerative MediaTraining

inworld-ai

Realtime speech-to-speech and expressive TTS-2 text-to-speech.

ttsfine-tunespeech-to-speechreal-time

Tool

Gorilla

QATraining

ShishirPatil

Fine-tuned models, datasets, and the Berkeley leaderboard for training and evaluating LLM API and function calling

tool-callingevaluationhuggingfacedataset

Adaptive Engine

TrainingInferenceQA

RLOps platform for continuously fine-tuning, evaluating and serving specialised LLMs from production feedback (company acquired by Datadog).

rlopsfine-tuneproduction-feedback

Entry Point AI

TrainingData WranglingInference

No-code platform for prompt-based data transforms, synthetic example generation and fine-tuning/deploying custom models.

fine-tunesynthetic-datadataset-managementagent-builder

RunPod

DeploymentTrainingInference

GPU cloud offering Pods, autoscaling Serverless workers, multi-node Clusters and a repo-backed Hub for one-click model endpoints.

gpucloudserverlessautoscaling