Infini-AI-Lab / UMbreLLaLinks
LLM Inference on consumer devices
☆124Updated 6 months ago
Alternatives and similar repositories for UMbreLLa
Users that are interested in UMbreLLa are comparing it to the libraries listed below
Sorting:
- ☆152Updated 3 months ago
- ☆60Updated 3 months ago
- Samples of good AI generated CUDA kernels☆91Updated 4 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆125Updated last month
- Sparse Inferencing for transformer based LLMs☆201Updated last month
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- ☆98Updated last month
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆270Updated this week
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆148Updated this week
- scalable and robust tree-based speculative decoding algorithm☆359Updated 8 months ago
- ☆218Updated 8 months ago
- ☆440Updated last month
- GPTQ and efficient search for GGUF☆50Updated 3 weeks ago
- ☆58Updated 4 months ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆304Updated 4 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆234Updated 10 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆196Updated 4 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆247Updated 8 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆201Updated last year
- Code for data-aware compression of DeepSeek models☆54Updated 3 months ago
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees" adapted for Llama models☆40Updated 2 years ago
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆247Updated last year
- 1.58-bit LLaMa model☆82Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆164Updated last week
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆111Updated last week
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 11 months ago
- Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.☆165Updated last year
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆53Updated this week
- Work in progress.☆74Updated 3 months ago
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning☆193Updated last month