foundation-model-stack / fms-extras
☆24Updated 5 months ago
Alternatives and similar repositories for fms-extras:
Users that are interested in fms-extras are comparing it to the libraries listed below
- A safetensors extension to efficiently store sparse quantized tensors on disk☆75Updated this week
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆40Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆148Updated 3 weeks ago
- ☆40Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆59Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆107Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆64Updated 5 months ago
- ☆125Updated last year
- PyTorch building blocks for the OLMo ecosystem☆54Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆229Updated this week
- Make triton easier☆44Updated 8 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆91Updated last year
- Code for studying the super weight in LLM☆80Updated 2 months ago
- A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.☆80Updated 2 weeks ago
- Example of applying CUDA graphs to LLaMA-v2☆11Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆57Updated 3 weeks ago
- Triton-based implementation of Sparse Mixture of Experts.☆196Updated 2 months ago
- ☆59Updated 2 weeks ago
- ☆42Updated last year
- ☆111Updated this week
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆116Updated 2 months ago
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 7 months ago
- ☆100Updated 5 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆89Updated this week
- Easy and Efficient Quantization for Transformers☆193Updated 2 weeks ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆114Updated 8 months ago
- This repository contains the experimental PyTorch native float8 training UX☆221Updated 6 months ago
- Experiments on speculative sampling with Llama models☆124Updated last year