Search Results for "triton"
Sort By:
Showing 26 open source projects for "triton"
View related business solutions-
8 Monitoring Tools in One APM. Install in 5 Minutes.AppSignal works out of the box for Ruby, Elixir, Node.js, Python, and more. 30-day free trial, no credit card required.
-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
Triton
Development repository for the Triton language and compiler
Triton is a programming language and compiler framework specifically designed for writing highly efficient custom deep learning operations, particularly for GPUs. It aims to bridge the gap between low-level GPU programming, such as CUDA, and higher-level abstractions by providing a more productive and flexible environment for developers. -
2
Triton Inference Server
The Triton Inference Server provides an optimized cloud
Triton Inference Server is an open-source inference serving software that streamlines AI inferencing. Triton enables teams to deploy any AI model from multiple deep learning and machine learning frameworks, including TensorRT, TensorFlow, PyTorch, ONNX, OpenVINO, Python, RAPIDS FIL, and more. Triton supports inference across cloud, data center, edge, and embedded devices on NVIDIA GPUs, x86 and ARM CPU, or AWS Inferentia. -
3
Une nouvelle édition particulièrement adaptée aux francophones du monde entier. Un petit linux qui a tout d'un grand, complet, léger, véloce et au design soigné comme toutes les versions précédentes et facilement personnalisable.
-
4
TensorRT LLM
TensorRT LLM provides users with an easy-to-use Python API
...It includes support for cutting-edge inference methods like speculative decoding and inflight batching, enabling real-time and large-scale AI applications. TensorRT-LLM integrates seamlessly with NVIDIA’s broader inference ecosystem, including Triton Inference Server and distributed deployment frameworks, making it suitable for production environments. -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
5
gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models
...Both models use a native MXFP4 quantization for efficient memory use and support OpenAI’s Harmony response format, enabling transparent full chain-of-thought reasoning and advanced tool integrations such as function calling, browsing, and Python code execution. The repository provides multiple reference implementations—including PyTorch, Triton, and Metal—for educational and experimental use, as well as example clients and tools like a terminal chat app and a Responses API server. -
6
Liger Kernel
Efficient Triton Kernels for LLM Training
Liger Kernel is a unified kernel developed by LinkedIn to streamline data science and machine learning workflows across different languages and tools. It provides a consistent interface for running code in various languages (such as Python, R, SQL) within a single Jupyter-like environment, enhancing productivity and collaboration for data scientists working in mixed-language projects. -
7
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
how-to-optim-algorithm-in-cuda is an open educational repository focused on teaching developers how to optimize algorithms for high-performance execution on GPUs using CUDA. The project combines technical notes, code examples, and practical experiments that demonstrate how common computational kernels can be optimized to improve speed and memory efficiency. Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations... -
8
Spark TTS
Spark-TTS Inference Code
Spark TTS is an open-source, PyTorch-based text-to-speech inference system that leverages large language models to produce highly natural, intelligible speech from text input. It uses an efficient single-stream architecture where speech tokens are directly reconstructed from the predictions of an LLM, removing the need for external acoustic models or complex vocoders and making the generation pipeline cleaner and faster. The project supports zero-shot voice cloning, meaning it can imitate a... -
9
Description TRITON-8.0 est une distribution Linux essentiellement destinée aux francophones. Triton-8.0 est basé sur JammyPup32 (UPupJJ+D-22.04) JammyJellyfish+Debian du 14-Nov-2022 développé par peebee Il est simple, complet, léger, convivial, réactif, véloce, beau et, bien sûr, gratuit. Commode pour une utilisation courante de tous les jours.
-
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
10
FasterTransformer
Transformer related optimization, including BERT, GPT
...It provides optimized implementations of transformer encoder and decoder layers using CUDA, cuBLAS, and custom kernels to maximize throughput and minimize latency. The library supports multiple deep learning frameworks, including TensorFlow, PyTorch, and Triton, allowing developers to integrate it into existing pipelines without major changes. It includes advanced optimization techniques such as mixed precision, tensor parallelism, and efficient memory management, enabling large models to run across multiple GPUs and nodes. FasterTransformer is particularly focused on inference workloads, where it significantly improves performance compared to standard framework implementations. ... -
11
Triton
Triton is a dynamic binary analysis library
Triton is a dynamic binary analysis library. It provides internal components that allow you to build your program analysis tools, automate reverse engineering, perform software verification or just emulate code. Linux, Windows and OS X compatible. You can directly compile source code from our Github repository. The Triton library is Linux, Windows and OS X compatible. -
12
Hugging Face Transformer
CPU/GPU inference server for Hugging Face transformer models
...Most tutorials on Transformer deployment in production are built over Pytorch and FastAPI. Both are great tools but not very performant in inference. Then, if you spend some time, you can build something over ONNX Runtime and Triton inference server. You will usually get from 2X to 4X faster inference compared to vanilla Pytorch. It's cool! However, if you want the best in class performances on GPU, there is only a single possible combination: Nvidia TensorRT and Triton. You will usually get 5X faster inference compared to vanilla Pytorch. -
13
-
14
img2key
Collection d'utilitaires pour supports USB
---fr_FR--- Ce programme a été écrit en gambas3-3.10.0 pour la distribution ToOpPy V2.2 et, est constitué de plusieurs modules regroupés en une seule interface. ---en_GB--- This program was written in gambas3-3.10.0 for the ToOpPy V2.2 distribution and consists of several modules grouped into a single interface. -
15
crearch
Aide à la création d'archives => Help in the creation of archives
---fr_FR--- Crearch est destiné aux distributions "puppy-linux" comme ToOpPy, Triton, Tahr, etc. Didacticiel inclus. nombreux outils inclus (comparaison des librairies, prévisualisation du contenu des fichiers etc.). Facilité d'utilisation par simple glisser déposer dans les divers contrôles, configuration de l'interface modulaire. ---en_GB--- Crearch is intended for "puppy-linux" distributions such as ToOpPy, Triton, Tahr, etc. -
16
Description TRITON-6.0 est une distribution Linux francophone basée sur puppy-tahr-6.0.5. Triton est simple, complet, léger, convivial, réactif, véloce, beau et, bien sûr, gratuit. Commode pour une utilisation courante de tous les jours. Il est parfait pour une utilisation nomade sur clé usb et peut être très utile pour redonner vie à un pc qui a pris de l'âge.
-
17
-
18
TRITON 5.7.3 est une distribution Linux basée sur Puppy precise 5.7. Triton est simple, complet , léger, convivial, réactif, véloce et beau. Il est parfait pour une utilisation nomade sur sur clé usb. * Vous avez le choix entre cinq grands navigateurs : Firefox - Google-chrome - Palemoon - Maxthon ou Opera. Avec ses compléments, Triton vous offre : * La suite bureautique complète LibreOffice en version 4.1.2.3 * Skype 4.3 pour Linux
-
19
Triton5.7.2
Distribution Linux francophone basée sur Puppy precise 5.7.
TRITON 5.7(2) est une distribution Linux basée sur Puppy precise 5.7. Triton est simple, complet , léger, convivial, réactif, véloce et beau. Il est parfait pour une utilisation nomade sur sur clé usb. * Vous avez le choix entre cinq grands navigateurs : Firefox - Google-chrome - Palemoon - Maxthon ou Opera. Avec ses compléments, Triton vous offre : * La suite bureautique complète LibreOffice en version 4.1.2.3 * Skype 4.2 pour Linux -
20
TRITON 5.7.2 bis est une distribution Linux basée sur Puppy precise 5.7. Simple, complet , léger, convivial, réactif, véloce et beau. Il est parfait pour une utilisation nomade sur sur clé usb. * Vous avez le choix entre cinq grands navigateurs : Firefox - Google-chrome - Palemoon - Maxthon ou Opera. Avec ses compléments, Triton vous offre : * La suite bureautique complète LibreOffice en version 4.1.2.3 * Skype 4.2 pour Linux
-
21
pyxtf
XTF (eXtended Triton Format) viewer and converter
-
22
User Interface Application authoring tool and MHEG-5 application generator. Additionally the Triton MHEG-5 PC Simulation Tool can be purchased for £300. Click the Project Homepage to buy this.
-
23
Triton CMS is not just yet another CMS; it is built on an extensible framework (Triton), which aims at high scalability, high performance and high security. Triton CMS comes with an easy-to-use Windows -like graphical user interface.
-
24
This project is an instant messenger created in a one man team(me) and soon maybe grow and create a wonderful instant messenger alternative.
-
25
ALCHEMIST is a Korg Trinity to Triton PCG and SNG converter. KORGLIB is a set of C libraries to access Trinity, Triton and Z1 PCG/SNG data.
