NimbleEdge / sparse_transformersLinks
Sparse Inferencing for transformer based LLMs
☆201Updated 2 months ago
Alternatives and similar repositories for sparse_transformers
Users that are interested in sparse_transformers are comparing it to the libraries listed below
Sorting:
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆42Updated last week
- InferX: Inference as a Service Platform☆136Updated this week
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆92Updated 5 months ago
- ☆135Updated 5 months ago
- LLM Inference on consumer devices☆124Updated 7 months ago
- AI management tool☆121Updated 11 months ago
- Enhancing LLMs with LoRA☆169Updated last month
- ☆158Updated 6 months ago
- DFloat11: Lossless LLM Compression for Efficient GPU Inference☆550Updated 2 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆94Updated 5 months ago
- Super simple python connectors for llama.cpp, including vision models (Gemma 3, Qwen2-VL). Compile llama.cpp and run!☆27Updated 2 months ago
- ☆62Updated 3 months ago
- ☆168Updated 2 months ago
- Testing LLM reasoning abilities with family relationship quizzes.☆62Updated 8 months ago
- Guaranteed Structured Output from any Language Model via Hierarchical State Machines☆145Updated 2 weeks ago
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆125Updated last week
- automatically quant GGUF models☆214Updated last week
- Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on differe…☆81Updated this week
- Local Qwen3 LLM inference. One easy-to-understand file of C source with no dependencies.☆140Updated 3 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆79Updated last year
- ☆60Updated 4 months ago
- ☆104Updated 2 months ago
- A pipeline parallel training script for LLMs.☆159Updated 5 months ago
- ☆31Updated 7 months ago
- Serving LLMs in the HF-Transformers format via a PyFlask API☆71Updated last year
- Dia-JAX: A JAX port of Dia, the text-to-speech model for generating realistic dialogue from text with emotion and tone control.☆27Updated 5 months ago
- ☆215Updated 3 weeks ago
- Chat WebUI is an easy-to-use user interface for interacting with AI, and it comes with multiple useful built-in tools such as web search …☆46Updated last month
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆127Updated 2 months ago
- VLLM Port of the Chatterbox TTS model☆318Updated last week