TokenSpeed

DwarfStar is a self-contained, model-specific native inference engine for running DeepSeek V4 Flash, GLM 5.2, and, on high-memory systems, DeepSeek V4 PRO locally. It combines model loading, prompt rendering, tool calls, persistent KV state, an HTTP server, and a coding agent rather than serving as a general GGUF runner. The engine supports Metal on Macs, CUDA including multi-GPU systems, and ROCm on Strix Halo hardware; it also provides SSD streaming for machines with insufficient RAM, distributed tensor and pipeline parallelism, and server-side micro-batching for multi-user inference. The repository includes tooling and data for GGUF, imatrix, quality, and speed testing, and acknowledges code and design contributions from llama.cpp and GGML.

GuideLLM is an open-source platform for benchmarking and evaluating real-world LLM inference deployments. It simulates end-to-end interactions with OpenAI-compatible and vLLM-native servers, using real or synthetic text and multimodal datasets and configurable execution profiles such as synchronous, concurrent, throughput, constant-rate, Poisson, and sweep workloads. It measures SLO-oriented latency and token statistics, including time to first token, inter-token latency, and end-to-end behavior, then produces console, JSON, CSV, or HTML reports for deployment tuning, capacity planning, and regression tracking. The tool provides both a CLI and API, with multiprocessing, threading, asynchronous execution, and Hugging Face, file, synthetic, or custom data sources.

slotstream is an open-source macOS local-LLM inference engine that runs Qwen3.8-Flash-Next, a 125-billion-parameter mixture-of-experts model, on Apple Silicon Macs whose memory cannot hold the model. Implemented as a single Swift binary using MLX, it keeps the dense trunk resident and reads routed expert weights from an SSD into a shared cache of slots, sizing that cache to available memory instead of loading the full model. It supports prefix caching for follow-up turns and exposes Ollama-compatible and OpenAI-compatible chat APIs, as well as a command-line prompt mode; the documented API subset supports streaming, CORS, and sampling options but not tools, images, JSON-schema output, or logprobs. The project requires macOS 14 or later, Apple Silicon, and roughly 110 GB of free disk space for the model weights. Its installer provides signed release binaries, and the repository can also be built with Swift and the macOS Command Line Tools. The source is MIT-licensed; the model weights are distributed under the Qwen community license.

SGLang is an open-source serving framework and inference engine for large language models and multimodal models, developed by the SGLang project. It provides an alternative serving stack for deployed models, with runtime and kernel optimizations for inference workloads. Its documented capabilities include RadixAttention, a zero-overhead batch scheduler, cache-aware load balancing, structured-output decoding, speculative decoding, disaggregated prefill and decode, model parallelism, and support for GPU and TPU backends. The project also publishes integrations and optimizations for current open models and multimodal, image, and video-generation workloads.

vLLM is an open-source library and inference-serving engine for deploying large language models on GPUs and other hardware accelerators. Originally developed in UC Berkeley's Sky Computing Lab, it is maintained by a broad community and provides an OpenAI-compatible API server, as well as Anthropic Messages API and gRPC support. Its serving stack manages attention key-value memory with PagedAttention, continuous batching, chunked prefill, prefix caching, streaming generation, and disaggregated prefill, decode, and encode. It also supports speculative decoding, quantization, optimized attention and GEMM/MoE kernels, automatic kernel generation and graph-level transformations, structured outputs, tool calling, multiple decoding algorithms, and distributed inference through tensor, pipeline, data, expert, and context parallelism. The project integrates with Hugging Face models and supports decoder-only, mixture-of-experts, hybrid state-space, multimodal, embedding, retrieval, reward, and classification models. It can run across NVIDIA, AMD, Intel, and other supported accelerators, as well as x86, ARM, and PowerPC CPUs, and can be installed with uv or pip or built from source.