Search Results for "compute"
Sort By:
Showing 31 open source projects for "compute"
View related business solutions-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
Application Monitoring That Won't Slow Your App DownFull APM with errors, performance, logs, and uptime monitoring. 99.999% uptime SLA on the platform itself.
-
1
Step 3.5 Flash
Fast, Sharp & Reliable Agentic Intelligence
...Unlike dense models that activate all their parameters for every token, Step 3.5 Flash uses a sparse Mixture-of-Experts (MoE) architecture that selectively engages only about 11 billion of its roughly 196 billion total parameters per token, delivering high-quality reasoning and interaction at far lower compute cost and latency than traditional large models. Its design targets deep reasoning, long-context handling, coding, and real-time responsiveness, making it suitable for building autonomous agents, advanced assistants, and long-chain cognitive workflows without sacrificing performance. -
2
DeepSeekMath-V2
Towards self-verifiable mathematical reasoning
DeepSeekMath-V2 is a large-scale open-source AI model designed specifically for advanced mathematical reasoning, theorem proving, and rigorous proof verification. It’s built by DeepSeek as a successor to their earlier math-specialist models. Unlike general-purpose LLMs that might generate plausible-looking math but sometimes hallucinate or mishandle rigorous logic, Math-V2 is engineered to not only generate solutions but also self-verify them, meaning it examines the derivations, checks... -
3
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. -
4
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
...The architecture incorporates advanced techniques such as mixture-of-experts routing, adaptive computation time, and multiple attention mechanisms to dynamically allocate compute where needed. It is highly configurable through a centralized configuration system, allowing experimentation with different architectural parameters such as loop depth, attention type. -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
5
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
...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
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 trade-off: somewhat reduced capacity compared to 4.5V or 4.6V, but with benefits in terms of speed, deployability, and lower hardware requirements — making it especially useful for developers experimenting locally, building lightweight agents, or deploying on limited infrastructure. ... -
7
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
...It is built on the MiniMax-Text-01 foundation and keeps the same massive parameter budget, but reworks the attention and training setup for better reasoning and test-time compute scaling. Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to support a native context length of 1 million tokens while using far fewer FLOPs than comparable reasoning models for very long generations. The team emphasizes efficient scaling of test-time compute: at 100K-token generation lengths, M1 reportedly uses only about 25 percent of the FLOPs of some competing models, making extended “think step” traces more feasible. ... -
8
DeepSeek Coder
DeepSeek Coder: Let the Code Write Itself
DeepSeek-Coder is a series of code-specialized language models designed to generate, complete, and infill code (and mixed code + natural language) with high fluency in both English and Chinese. The models are trained from scratch on a massive corpus (~2 trillion tokens), of which about 87% is code and 13% is natural language. This dataset covers project-level code structure (not just line-by-line snippets), using a large context window (e.g. 16K) and a secondary fill-in-the-blank objective... -
9
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for... -
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.
-
10
OpenTinker
OpenTinker is an RL-as-a-Service infrastructure for foundation models
...Traditional RL setups can be monolithic and difficult to configure, but OpenTinker separates concerns across agent definition, environment interaction, and execution, which lets developers focus on defining the logic of agents and environments separately from how training and inference are run. It introduces a centralized scheduler to manage distributed training jobs and shared compute resources, enabling workloads like reinforcement learning, supervised fine-tuning, and inference to run across multiple settings. The architecture supports a range of single-turn and multi-turn agentic tasks with a design that abstracts away infrastructure complexity while offering flexible Python APIs to define environments and workflows. -
11
Ling
Ling is a MoE LLM provided and open-sourced by InclusionAI
Ling is a Mixture-of-Experts (MoE) large language model (LLM) provided and open-sourced by inclusionAI. The project offers different sizes (Ling-lite, Ling-plus) and emphasizes flexibility and efficiency: being able to scale, adapt expert activation, and perform across a range of natural language/reasoning tasks. Example scripts, inference pipelines, and documentation. The codebase includes inference, examples, models, documentation, and model download infrastructure. As more developers and... -
12
Ling-V2
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI
Ling-V2 is an open-source family of Mixture-of-Experts (MoE) large language models developed by the InclusionAI research organization with the goal of combining state-of-the-art performance, efficiency, and openness for next-generation AI applications. It introduces highly sparse architectures where only a fraction of the model’s parameters are activated per input token, enabling models like Ling-mini-2.0 to achieve reasoning and instruction-following capabilities on par with much larger... -
13
Granite 3.0 Language Models
New set of lightweight state-of-the-art, open foundation models
This repository introduces Granite 3.0 language models as lightweight, state-of-the-art open foundation models built to natively support multilinguality, coding, reasoning, and tool usage. A central goal is efficient deployment, including the potential to run on constrained compute resources while remaining useful for a broad span of enterprise tasks. The repo positions the models for both research and commercial use under an Apache-2.0 license, signaling permissive adoption paths. Documentation highlights the capability mix (reasoning, tool use, code) and points to model artifacts and guidance for evaluation. ... -
14
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
...The repository provides training logic, adaptation strategies (e.g. prompt tuning, adapter modules), and evaluation across base and target domains to measure how well the model retains its general knowledge while specializing as needed. It includes utilities to fine-tune vision-language embeddings, compute prompt or adapter updates, and benchmark across transfer and retention metrics. MetaCLIP is especially suited for real-world settings where a model must continuously incorporate new visual categories or domains over time. -
15
Profile Data
Analyze computation-communication overlap in V3/R1
profile-data is a repository that publishes profiling traces and metrics from DeepSeek’s training and inference infrastructure (especially during DeepSeek-V3 / R1 experiments). The profiling data targets insights into computation-communication overlap, pipeline scheduling (e.g. DualPipe), and how MoE / EP / parallelism strategies interact in real systems. The repository contains JSON trace files like train.json, prefill.json, decode.json, and associated assets. Users can load them into tools... -
16
gpt-oss-safeguard
Safety reasoning models built-upon gpt-oss
...The model comes in at least two variants: a large 120B-parameter version for heavy-duty, high-accuracy reasoning, and a 20B-parameter version optimized for lower latency or smaller compute resources. At inference time you supply both the content and your own safety policy (written in a structured prompt), and the model will evaluate the content and return its justification — enabling transparent, auditable moderation decisions. It supports running fully locally or in private infrastructure (no mandatory cloud dependence). -
17
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... -
18
DeepSeek MoE
Towards Ultimate Expert Specialization in Mixture-of-Experts Language
DeepSeek-MoE (“DeepSeek MoE”) is the DeepSeek open implementation of a Mixture-of-Experts (MoE) model architecture meant to increase parameter efficiency by activating only a subset of “expert” submodules per input. The repository introduces fine-grained expert segmentation and shared expert isolation to improve specialization while controlling compute cost. For example, their MoE variant with 16.4B parameters claims comparable or better performance to standard dense models like DeepSeek 7B or LLaMA2 7B using about 40% of the total compute. The repo publishes both Base and Chat variants of the 16B MoE model (deepseek-moe-16b) and provides evaluation results across benchmarks. ... -
19
FastViT
This repository contains the official implementation of research
...The codebase provides reference implementations and checkpoints that make it easy to evaluate or fine-tune on downstream datasets. In practice, FastViT offers drop-in backbones that reduce compute and memory pressure without exotic training tricks. -
20
TimeSformer
The official pytorch implementation of our paper
...TimeSformer was influential in showing that pure transformer architectures—without convolutional backbones—can perform strongly on video classification tasks. Its flexible attention design allows experimenting with different factoring (spatial-then-temporal, joint, etc.) to trade off compute, memory, and accuracy. -
21
PyTorch-BigGraph
Generate embeddings from large-scale graph-structured data
PyTorch-BigGraph (PBG) is a system for learning embeddings on massive graphs—think billions of nodes and edges—using partitioning and distributed training to keep memory and compute tractable. It shards entities into partitions and buckets edges so that each training pass only touches a small slice of parameters, which drastically reduces peak RAM and enables horizontal scaling across machines. PBG supports multi-relation graphs (knowledge graphs) with relation-specific scoring functions, negative sampling strategies, and typed entities, making it suitable for link prediction and retrieval. ... -
22
Nemotron 3
Large language model developed and released by NVIDIA
NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 is a state-of-the-art large language model developed and released by NVIDIA as part of its Nemotron 3 family, optimized for high-efficiency inference and strong reasoning performance in open AI workloads. It is the post-trained and FP8-quantized variant of the Nemotron 3 Nano model, meaning its weights and activations are represented in 8-bit floating point (FP8) to dramatically reduce memory usage and computational cost while retaining high accuracy. The... -
23
DeepSeek-V3.2-Speciale
High-compute ultra-reasoning model surpassing model surpassing GPT-5
DeepSeek-V3.2-Speciale is the high-compute, ultra-reasoning variant of DeepSeek-V3.2, designed specifically to push the boundaries of mathematical, logical, and algorithmic intelligence. It builds on the DeepSeek Sparse Attention (DSA) framework, delivering dramatically improved long-context efficiency while preserving full model quality. Unlike the standard version, Speciale is tuned exclusively for deep reasoning and therefore does not support tool-calling, focusing its full capacity on pure cognitive performance. ... -
24
DeepSeek-V4-Pro
Flagship MoE model for advanced reasoning, coding, and agents
...The model supports an ultra-long context window of up to 1 million tokens, making it highly suitable for long-document reasoning, large codebases, and complex multi-step tasks. Architecturally, it introduces optimizations to reduce compute and memory costs while improving stability across long sequences. DeepSeek-V4-Pro is positioned as the high-end variant of the V4 family, outperforming most open-source models in areas such as agentic coding, STEM reasoning, and world knowledge, and approaching the performance of leading closed-source systems. It also supports advanced reasoning modes and tool-based workflows, enabling autonomous task execution. -
25
BLEURT-20-D12
Custom BLEURT model for evaluating text similarity using PyTorch
...Unlike standard BLEURT models from TensorFlow, this version is built from a custom PyTorch transformer library. It requires installing the model-specific library from GitHub to function properly. Once set up, it can be used to compute similarity scores with minimal code. BLEURT-20-D12 enables more flexible deployment in PyTorch-based workflows for evaluating language generation outputs.
