Search Results for "gpu max performance"
Sort By:
Showing 155 open source projects for "gpu max performance"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
1
AGI (Android GPU Inspector)
Android GPU Inspector
Android GPU Inspector (AGI) is a desktop tool for profiling, tracing, and debugging graphics workloads running on Android devices. It helps developers analyze Vulkan and OpenGL ES applications at the system, frame, and draw-call levels to uncover GPU and CPU bottlenecks. AGI captures detailed performance counters, timelines, and pipeline state to reveal stalls, overdraw, shader hotspots, and inefficient resource usage. -
2
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
...These examples show how different optimization techniques influence performance on modern GPU hardware and allow readers to experiment with real implementations. The repository also contains extensive learning notes that summarize CUDA programming concepts, GPU architecture details, and performance engineering strategies. -
3
Fabulously Optimized
A simple Minecraft modpack focusing on performance and graphics
A simple Minecraft modpack focusing on performance and graphics enhancements. A Minecraft modpack focused on performance, providing a smooth experience with multiple optimization mods. -
4
CUDA Python
Performance meets Productivity
CUDA Python is a unified Python interface for accessing and working with the NVIDIA CUDA platform, enabling developers to build GPU-accelerated applications entirely in Python. It acts as a metapackage composed of multiple submodules that provide both high-level and low-level access to CUDA functionality, including runtime APIs, driver APIs, and JIT compilation tools. The project is designed to simplify GPU programming by offering Pythonic abstractions while still exposing the full power of... -
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
Triton
Development repository for the Triton language and compiler
...The project leverages LLVM and MLIR to compile code into efficient GPU instructions, supporting both NVIDIA and AMD hardware. It is widely used in research and production environments where custom tensor operations are required, offering both high performance and developer-friendly syntax. -
6
NVIDIA Warp
A Python framework for accelerated simulation, data generation
NVIDIA Warp is a high-performance Python framework developed by NVIDIA for building and accelerating simulation, graphics, and physics-based workloads using GPU computing. It enables developers to write kernel-level code in Python that is automatically compiled into efficient CUDA kernels, combining ease of use with near-native performance. The framework is designed for applications such as robotics, reinforcement learning, physical simulation, and differentiable computing, where performance and flexibility are critical. ... -
7
OpenLIT
OpenLIT is an open-source LLM Observability tool
OpenLIT is an OpenTelemetry-native tool designed to help developers gain insights into the performance of their LLM applications in production. It automatically collects LLM input and output metadata and monitors GPU performance for self-hosted LLMs. OpenLIT makes integrating observability into GenAI projects effortless with just a single line of code. Whether you're working with popular LLM providers such as OpenAI and HuggingFace, or leveraging vector databases like ChromaDB, OpenLIT ensures your applications are monitored seamlessly, providing critical insights including GPU performance stats for self-hosted LLMs to improve performance and reliability. ... -
8
Pruna AI
Pruna is a model optimization framework built for developers
Pruna is an open-source, self-hostable AI inference engine designed to help teams deploy and manage large language models (LLMs) efficiently across private or hybrid infrastructures. Built with performance and developer ergonomics in mind, Pruna simplifies inference workflows by enabling multi-model orchestration, autoscaling, GPU resource allocation, and compatibility with popular open-source models. It is ideal for companies or teams looking to reduce reliance on external APIs while maintaining speed, cost-efficiency, and full control over their data and AI stack. ... -
9
GPUStack
Performance-optimized AI inference on your GPUs
GPUStack is an open-source GPU cluster management platform designed to simplify the deployment and operation of artificial intelligence models across heterogeneous hardware environments. The system aggregates GPU resources from multiple machines into a unified cluster so developers and administrators can run large language models and other AI workloads efficiently across distributed infrastructure. Instead of requiring complex orchestration systems such as Kubernetes, GPUStack provides a... -
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
10
PEFT
State-of-the-art Parameter-Efficient Fine-Tuning
Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of pre-trained language models (PLMs) to various downstream applications without fine-tuning all the model's parameters. Fine-tuning large-scale PLMs is often prohibitively costly. In this regard, PEFT methods only fine-tune a small number of (extra) model parameters, thereby greatly decreasing the computational and storage costs. Recent State-of-the-Art PEFT techniques achieve performance comparable to that of full... -
11
FlashKDA
High-performance Kimi Delta Attention kernels
...Builds can target the detected GPU architecture or multiple supported architectures for wheels and CI pipelines. The repository also provides correctness tests, benchmark material, a direct Python kernel API, and development helpers for CUDA and C++ tooling. -
12
FlashAttention
Fast and memory-efficient exact attention
FlashAttention is a high-performance deep learning optimization library that reimplements the attention mechanism used in transformer models to be significantly faster and more memory-efficient than standard implementations. It achieves this by using IO-aware algorithms that minimize memory reads and writes, reducing the quadratic memory overhead typically associated with attention operations. -
13
autoresearch-macos
AI agents running research on single-GPU nanochat training
autoresearch-macos is a macOS-focused adaptation of autonomous research loop systems inspired by the autoresearch paradigm, enabling AI agents to iteratively improve machine learning models through self-directed experimentation. The system follows a structured loop in which an agent modifies a training script, executes a fixed-duration experiment, evaluates performance metrics, and decides whether to keep or revert changes. It is designed to operate efficiently within macOS environments, making it accessible for developers working outside traditional high-performance GPU clusters. The project typically includes components such as data preparation scripts, a training loop, and an instruction file that guides the agent’s behavior. ... -
14
Numba CUDA Target
The CUDA target for Numba
Numba CUDA Target is NVIDIA’s maintained CUDA backend for the Numba JIT compiler, enabling developers to write GPU-accelerated code directly in Python. It allows users to define CUDA kernels using Python syntax, which are then compiled into efficient GPU code at runtime using LLVM-based toolchains. This approach significantly lowers the barrier to entry for GPU programming by eliminating the need to write CUDA C++ while still delivering high performance. -
15
Meridian
Meridian is an MMM framework
...Meridian uses the No-U-Turn Sampler (NUTS) for Markov Chain Monte Carlo (MCMC) sampling to produce statistically rigorous results, and it includes GPU acceleration to significantly reduce computation time. -
16
NVIDIA cuOpt
GPU accelerated decision optimization
...The platform provides multiple interfaces, including C, Python, and server APIs, allowing developers to integrate optimization capabilities into applications and services. cuOpt is designed for high-performance environments and can be deployed across cloud, hybrid, or on-premise infrastructures. By combining GPU acceleration with scalable APIs, cuOpt enables organizations to solve large optimization challenges in logistics, operations research, and decision-making systems. -
17
Newton
An open-source, GPU-accelerated physics simulation engine
Newton is a high-performance, GPU-accelerated physics simulation engine designed primarily for robotics research, machine learning, and advanced simulation workflows. Built on top of NVIDIA Warp, it leverages GPU parallelism to deliver scalable and efficient simulation environments that support rapid iteration and experimentation. The engine extends previous simulation frameworks by introducing differentiable physics capabilities, allowing it to integrate seamlessly with machine learning models and optimization pipelines. ... -
18
Megatron-LM
Ongoing research training transformer models at scale
Megatron-LM is a GPU-optimized deep learning framework from NVIDIA designed to train extremely large transformer-based language models efficiently at scale. The repository provides both a reference training implementation and Megatron Core, a composable library of high-performance building blocks for custom large-model pipelines. It supports advanced parallelism strategies including tensor, pipeline, data, expert, and context parallelism, enabling training across massive multi-GPU and multi-node clusters. ... -
19
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
...These capabilities aim to lower latency, cut GPU cycles, and stabilize performance for production workloads with overlapping prompts or retrieval-augmented contexts. The end result is a cache fabric for LLMs that complements engines rather than replacing them. -
20
LTX-2
Python inference and LoRA trainer package for the LTX-2 audio–video
LTX-2 is a powerful, open-source toolkit developed by Lightricks that provides a modular, high-performance base for building real-time graphics and visual effects applications. It is architected to give developers low-level control over rendering pipelines, GPU resource management, shader orchestration, and cross-platform abstractions so they can craft visually compelling experiences without starting from scratch. Beyond basic rendering scaffolding, LTX-2 includes optimized math libraries, resource loaders, utilities for texture and buffer handling, and integration points for native event loops and input systems. ... -
21
Alpamayo 1
Bridging Reasoning and Action Prediction
...It incorporates vision-language-action modeling, enabling it to process sensor data and contextual information simultaneously. Alpamayo supports tasks such as trajectory prediction, auto-labeling, and reasoning-based decision making. The system is optimized for high-performance GPU environments and is intended primarily for experimentation and benchmarking. Overall, it represents an advanced step toward integrating reasoning into autonomous driving pipelines. -
22
Faster Whisper
Faster Whisper transcription with CTranslate2
Faster Whisper is an optimized implementation of the Whisper speech recognition model designed to deliver significantly faster inference while maintaining comparable accuracy. It leverages efficient inference engines and optimized computation strategies to reduce latency and resource consumption. The system is particularly useful for real-time or large-scale transcription tasks where performance is critical. It supports multiple model sizes, allowing users to balance speed and accuracy based... -
23
Modular Platform
The Modular Platform (includes MAX & Mojo)
Modular is a high-performance AI infrastructure company repository focused on building next-generation compute and software tools for machine learning workloads. The project centers on enabling developers to run AI models faster and more efficiently by rethinking the traditional ML software stack. It is closely associated with the Mojo programming language and related tooling that aims to combine Python usability with systems-level performance. Modular’s ecosystem is designed to simplify... -
24
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
...In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. The framework integrates several state-of-the-art methods such as PyramidKV, SnapKV, H2O, and StreamingLLM, allowing researchers to compare and experiment with different approaches within the same environment. ... -
25
Infinity
Low-latency REST API for serving text-embeddings
Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting all sentence-transformer models and frameworks. Infinity is developed under MIT License. Infinity powers inference behind Gradient.ai and other Embedding API providers.
