NimbleEdge / sparse_transformersLinks
Sparse Inferencing for transformer based LLMs
☆196Updated this week
Alternatives and similar repositories for sparse_transformers
Users that are interested in sparse_transformers are comparing it to the libraries listed below
Sorting:
- InferX is a Inference Function as a Service Platform☆119Updated last week
- DFloat11: Lossless LLM Compression for Efficient GPU Inference☆464Updated this week
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆39Updated 2 weeks ago
- LLM Inference on consumer devices☆123Updated 4 months ago
- ☆132Updated 3 months ago
- Local Qwen3 LLM inference. One easy-to-understand file of C source with no dependencies.☆97Updated last month
- ☆152Updated last week
- Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆93Updated last week
- Guaranteed Structured Output from any Language Model via Hierarchical State Machines☆141Updated 2 months ago
- Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on differe…☆67Updated last month
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆78Updated 10 months ago
- AI management tool☆118Updated 8 months ago
- ☆388Updated this week
- Super simple python connectors for llama.cpp, including vision models (Gemma 3, Qwen2-VL). Compile llama.cpp and run!☆25Updated 2 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆81Updated 2 months ago
- ☆94Updated 7 months ago
- Minimal Linux OS with a Model Context Protocol (MCP) gateway to expose local capabilities to LLMs.☆259Updated last month
- A pipeline parallel training script for LLMs.☆153Updated 3 months ago
- Lightweight Inference server for OpenVINO☆191Updated last week
- ☆155Updated 3 months ago
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.☆90Updated last month
- ☆58Updated 3 weeks ago
- ☆42Updated last month
- TPI-LLM: Serving 70b-scale LLMs Efficiently on Low-resource Edge Devices☆186Updated 2 months ago
- Smart proxy for LLM APIs that enables model-specific parameter control, automatic mode switching (like Qwen3's /think and /no_think), and…☆49Updated 2 months ago
- KoboldCpp Smart Launcher with GPU Layer and Tensor Override Tuning☆26Updated 2 months ago
- ☆27Updated 4 months ago
- Distributed Inference for mlx LLm☆94Updated last year
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆50Updated 5 months ago
- B-Llama3o a llama3 with Vision Audio and Audio understanding as well as text and Audio and Animation Data output.☆26Updated last year