Infini-AI-Lab / UMbreLLaLinks
LLM Inference on consumer devices
☆123Updated 4 months ago
Alternatives and similar repositories for UMbreLLa
Users that are interested in UMbreLLa are comparing it to the libraries listed below
Sorting:
- ☆44Updated last month
- ☆145Updated last month
- KV cache compression for high-throughput LLM inference☆134Updated 6 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆203Updated this week
- Samples of good AI generated CUDA kernels☆86Updated 2 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆116Updated 3 weeks ago
- ☆75Updated last month
- ☆54Updated 2 months ago
- Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆95Updated last week
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆288Updated 2 months ago
- scalable and robust tree-based speculative decoding algorithm☆354Updated 6 months ago
- Sparse Inferencing for transformer based LLMs☆196Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆142Updated this week
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆198Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆225Updated 8 months ago
- ☆215Updated 6 months ago
- ☆80Updated 8 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆266Updated 9 months ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆142Updated this week
- DFloat11: Lossless LLM Compression for Efficient GPU Inference☆464Updated last week
- Code for data-aware compression of DeepSeek models☆42Updated last month
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 9 months ago
- Simple extension on vLLM to help you speed up reasoning model without training.☆172Updated 2 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆648Updated 3 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆82Updated 2 months ago
- Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model☆233Updated 2 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆372Updated 3 months ago
- ☆388Updated last week
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆195Updated this week
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆244Updated 6 months ago