Search Results for "memory"
Sort By:
Showing 49 open source projects for "memory"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
1
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model
ChatGLM-6B is an open bilingual (Chinese + English) conversational language model based on the GLM architecture, with approximately 6.2 billion parameters. The project provides inference code, demos (command line, web, API), quantization support for lower memory deployment, and tools for finetuning (e.g., via P-Tuning v2). It is optimized for dialogue and question answering with a balance between performance and deployability in consumer hardware settings. Support for quantized inference (INT4, INT8) to reduce GPU memory requirements. Automatic mode switching between precision/memory tradeoffs (full/quantized). -
2
xFormers
Hackable and optimized Transformers building blocks
...One of its key goals is efficient attention: it supports dense, sparse, low-rank, and approximate attention mechanisms (e.g. FlashAttention, Linformer, Performer) via interchangeable modules. The library includes memory-efficient operator implementations in both Python and optimized C++/CUDA, ensuring that performance isn’t sacrificed for modularity. It also integrates with PyTorch seamlessly so you can drop in its blocks to existing models, replace default attention layers, or build new architectures from scratch. xformers includes training, deployment, and memory profiling tools. -
3
Mistral Finetune
Memory-efficient and performant finetuning of Mistral's models
mistral-finetune is an official lightweight codebase designed for memory-efficient and performant finetuning of Mistral’s open models (e.g. 7B, instruct variants). It builds on techniques like LoRA (Low-Rank Adaptation) to allow customizing models without full parameter updates, which reduces GPU memory footprint and training cost. The repo includes utilities for data preprocessing (e.g. reformat_data.py), validation scripts, and example YAML configs for training variants like 7B base or instruct models. ... -
4
Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion
...It also focuses on stability during long sessions, aiming to reduce out-of-memory failures and provide clearer diagnostics when they occur. The UI surfaces advanced options in a way that remains recognizable to WebUI users, so migration costs are low while gaining experimental features. In practice, Forge serves as a proving ground for ideas that may later influence upstream tools, giving power users early access to cutting-edge techniques. -
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
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
...It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to efficiently manage memory during decoding. On very compute-bound settings, it can reach up to ~660 TFLOPS on H800 SXM5 hardware, while in memory-bound configurations it can push memory throughput to ~3000 GB/s. The team regularly updates it with performance improvements; for example, a 2025 update claims 5 % to 15 % gains on compute-bound workloads while maintaining API compatibility. -
6
CodeGeeX2
CodeGeeX2: A More Powerful Multilingual Code Generation Model
...With improved inference efficiency, quantization options, and multi-query/flash attention, CodeGeeX2 achieves faster generation speeds and lightweight deployment, requiring as little as 6GB GPU memory at INT4 precision. Its backend powers the CodeGeeX IDE plugins for VS Code, JetBrains, and other editors, offering developers interactive AI assistance with features like infilling and cross-file completion. -
7
FramePack
Lets make video diffusion practical
...The idea is to “pack” frames by detecting shared structure and storing differences efficiently, which can accelerate training or inference on video-like data. By reducing I/O and memory bandwidth, datasets become lighter to load while models still see the essential temporal variation. The repository demonstrates both packing and unpacking steps, making it straightforward to integrate into preprocessing pipelines. It’s useful for diffusion and generative models that learn from sequential image datasets, as well as classical pipelines that batch many related frames. ... -
8
ACE-Step 1.5
The most powerful local music generation model
...It integrates cutting-edge generative techniques—such as diffusion-based synthesis combined with compressed autoencoders and lightweight transformer elements—to produce high-quality full-length music tracks with rapid inference times, capable of generating a complete song in seconds on modern GPUs while remaining efficient enough to run on consumer-grade hardware with minimal memory requirements. Beyond straightforward text-to-music synthesis, ACE-Step 1.5 enables flexible creative workflows, including tasks like cover generation, editing existing tracks, transforming vocals to background accompaniment, and stylistic personalization using low-rank adaptation from just a few example songs. -
9
ChatGLM.cpp
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
ChatGLM.cpp is a C++ implementation of the ChatGLM-6B model, enabling efficient local inference without requiring a Python environment. It is optimized for running on consumer hardware. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Map-Anything
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
...The model flexibly accepts different input combinations (images, intrinsics, poses, sparse or dense depth) and produces a rich set of outputs including per-pixel 3D points, camera intrinsics, camera poses, ray directions, confidence maps, and validity masks. Its inference path is fully feed-forward with optional mixed-precision and memory-efficient modes, making it practical to scale to long image sequences while keeping latency predictable. -
11
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
...Its architectures and training approaches are tuned to enable efficient and capable reasoning performance. Reasoning-optimized model with reinforcement learning enhancements. Efficient architecture and memory design for large-scale reasoning. If you are located in mainland China, we also provide the model on ModelScope.cn to speed up the download process. -
12
Tencent-Hunyuan-Large
Open-source large language model family from Tencent Hunyuan
...It is designed with long-context capabilities, quantization support, and high performance on benchmarks across general reasoning, mathematics, language understanding, and Chinese / multilingual tasks. It aims to provide competitive capability with efficient deployment and inference. FP8 quantization support to reduce memory usage (~50%) while maintaining precision. High benchmarking performance on tasks like MMLU, MATH, CMMLU, C-Eval, etc. -
13
HunyuanVideo-Avatar
Tencent Hunyuan Multimodal diffusion transformer (MM-DiT) model
HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces,... -
14
FLUX.2-klein-4B
Flux 2 image generation model pure C inference
...Because the implementation is in plain C and focuses on data locality and vectorized operations, flux2.c can be integrated into performance-critical code paths where control over memory layout and execution behavior matters, such as GPU kernels, embedded systems, or custom ML runtime engines. -
15
DeepSeek-V3.2-Exp
An experimental version of DeepSeek model
DeepSeek-V3.2-Exp is an experimental release of the DeepSeek model family, intended as a stepping stone toward the next generation architecture. The key innovation in this version is DeepSeek Sparse Attention (DSA), a sparse attention mechanism that aims to optimize training and inference efficiency in long-context settings without degrading output quality. According to the authors, they aligned the training setup of V3.2-Exp with V3.1-Terminus so that benchmark results remain largely... -
16
LingBot-World
Advancing Open-source World Models
LingBot-World is an open-source, high-fidelity world simulator designed to advance the state of world models through video generation. Built on top of Wan2.2, it enables realistic, dynamic environment simulation across diverse styles, including real-world, scientific, and stylized domains. LingBot-World supports long-term temporal consistency, maintaining coherent scenes and interactions over minute-level horizons. With real-time interactivity and sub-second latency at 16 FPS, it is... -
17
gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models
...The series includes two main models: gpt-oss-120b, a 117-billion parameter model optimized for general-purpose, high-reasoning tasks that can run on a single H100 GPU, and gpt-oss-20b, a lighter 21-billion parameter model ideal for low-latency or specialized applications on smaller hardware. 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. -
18
CogVideo
Text and image to video generation: CogVideoX and CogVideo
CogVideo is an open-source family of advanced video generation models that can create videos from text, images, or existing video inputs. Built on large-scale Transformer and diffusion architectures, it enables multimodal generation across text-to-video, image-to-video, and video continuation tasks. The latest CogVideoX models offer higher resolution outputs, longer video durations, and improved controllability through prompt engineering. The project includes tools for inference,... -
19
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
...It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). The repo supports multiple encodings (e.g. “cl100k_base”) and lets users switch encoding names to match different model contexts. It also offers extension mechanisms so that custom encodings can be registered. Internally, it includes the core tokenizer logic (often implemented in Rust or efficient lower-level code), APIs for encoding, decoding, and counting tokens, and binding layers to Python (and sometimes other languages) for easy use. -
20
HY-World 2.0
A Multi-Modal World Model for Reconstructing, Generating, Simulation
...For text and single-image inputs, it generates high-fidelity 3D Gaussian Splatting scenes through a multi-stage pipeline that includes panorama generation, trajectory planning, world expansion, and world composition. The system also improves reconstruction from multi-view images and video by upgrading its feed-forward 3D prediction components and its memory-aware view generation process. Another major part of the project is WorldLens, a rendering platform designed for interactive exploration with an engine-agnostic architecture, automatic image-based lighting, collision detection, and support for character interaction. -
21
Z80-μLM
Z80-μLM is a 2-bit quantized language model
...The project sits at the intersection of machine learning and systems constraints, showing how model architecture, quantization, and inference code generation can be adapted to extreme memory and compute limits. It also functions as an educational reference for how to reduce inference to operations that fit an old-school instruction set and runtime environment. -
22
DINOv2
PyTorch code and models for the DINOv2 self-supervised learning
...The repository includes code for training, evaluating, and feature extraction, with utilities to run k-NN or linear evaluation baselines to assess representation quality. Pretrained checkpoints cover multiple model sizes so practitioners can trade accuracy for speed and memory depending on their deployment constraints. -
23
ChatGPT Clone
ChatGPT interface with better UI
...The goal is to replicate the core chat UX—message history, streaming tokens, code blocks, and system prompts—while letting you plug in different provider APIs or local models. It showcases a clean separation between the web client and the message orchestration layer so you can experiment with prompts, roles, and memory strategies. The project is useful for prototyping assistants, documentation bots, and internal developer tools without committing to a specific vendor or UI framework. Configuration is kept simple so newcomers can get a working chat in minutes and then dial in features like authentication or multi-model routing. While it illustrates how to hook into third-party LLM endpoints, it is typically positioned as an educational, self-hosted starter that you should operate responsibly and within provider's terms of use. -
24
VibeThinker
Diversity-driven optimization and large-model reasoning ability
VibeThinker is a compact but high-capability open-source language model released by WeiboAI (Sina AI Lab). It contains about 1.5 billion parameters, far smaller than many “frontier” models, yet it is explicitly optimized for reasoning, mathematics, and code generation tasks rather than general open-domain chat. The innovation lies in its training methodology: the team uses what they call the Spectrum-to-Signal Principle (SSP), where a first stage emphasizes diversity of reasoning paths (the... -
25
GLM-4.1V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.1V — often referred to as a smaller / lighter version of the GLM-V family — offers a more resource-efficient option for users who want multimodal capabilities without requiring large compute resources. Though smaller in scale, GLM-4.1V maintains competitive performance, particularly impressive on many benchmarks for models of its size: in fact, on a number of multimodal reasoning and vision-language tasks it outperforms some much larger models from other families. It represents a...
