Search Results for "simple http server"

WASTE is an embeddable C inference engine for running extremely large mixture-of-experts models when the weights exceed available RAM. It keeps the shared model trunk in memory and streams only the experts selected for each token from fast NVMe storage. A bounded cache reuses recently needed experts, while lookahead routing begins disk reads before the next layer requires them. Its main target is the full 2.78-trillion-parameter Kimi K3 model, including multimodal image input. The engine has...

...The library includes definitions for all request and response parameters using Python typed objects, automatically handles serialization and deserialization, and wraps HTTP logic (timeouts, retries, error mapping) so that developers can call the API in a clean, high-level way. The SDK supports both synchronous and asynchronous usage (via async/await) depending on context. Importantly, it also supports streaming responses via Server-Sent Events (SSE) so that large outputs can be consumed incrementally rather than waiting for the full response. ...

...It focuses on bringing fast text-to-image generation to mainstream hardware like desktop CPUs, lower-end laptops, or edge devices without requiring high-end graphics processors. The repository contains multiple interfaces including a desktop GUI for simple generation, an advanced web-based UI with support for extensions like LoRA and ControlNet, and a command-line interface for scripted usage or server deployments. With support for performance-oriented libraries such as OpenVINO and hardware acceleration on platforms like Intel AI PCs, FastSD CPU aims to shrink generation times dramatically compared with naive CPU implementations.

...It is designed to let OpenAI-style clients connect to Gemini-like models through routes such as chat completions, models, responses, and native Gemini-compatible endpoints. The project can run as a simple local server and uses a mostly single-file design with an optional dependency for streaming. It supports model aliases for Flash, Thinking, Pro-style routing, Auto, and Lite variants. The tool also includes optional API keys, function calling, SSE streaming, web search access, Docker deployment, and client examples for OpenAI SDK-style usage. ...

Antigravity Claude Proxy is a purpose-built proxy server that enables developers to interface with Claude models through a standardized RESTful API, allowing tools and workflows that expect generic HTTP APIs to operate on Anthropic’s Claude without native support. The project acts as a translation layer, receiving web requests in common formats (such as OpenAI-style endpoints) and forwarding them to Anthropic’s API in the required structure, while converting responses back into a familiar shape. ...

FastViT is an efficient vision backbone family that blends convolutional inductive biases with transformer capacity to deliver strong accuracy at mobile and real-time inference budgets. Its design pursues a favorable latency-accuracy Pareto curve, targeting edge devices and server scenarios where throughput and tail latency matter. The models use lightweight attention and carefully engineered blocks to minimize token mixing costs while preserving representation power. Training and inference...