foundation-model-stack / fms-extrasLinks
β24Updated last year
Alternatives and similar repositories for fms-extras
Users that are interested in fms-extras are comparing it to the libraries listed below
Sorting:
- A safetensors extension to efficiently store sparse quantized tensors on diskβ161Updated this week
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β265Updated last month
- Experiments on speculative sampling with Llama modelsβ128Updated 2 years ago
- β74Updated 5 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".β277Updated last year
- β217Updated 7 months ago
- Benchmark suite for LLMs from Fireworks.aiβ83Updated 2 weeks ago
- This repository contains the experimental PyTorch native float8 training UXβ224Updated last year
- Easy and Efficient Quantization for Transformersβ203Updated 2 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clustersβ129Updated 9 months ago
- β111Updated last year
- π Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.β211Updated this week
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"β155Updated 11 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundryβ42Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMsβ266Updated 11 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.β46Updated last year
- Simple implementation of Speculative Sampling in NumPy for GPT-2.β96Updated 2 years ago
- β199Updated 4 months ago
- Load compute kernels from the Hubβ283Updated this week
- Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuningβ48Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsityβ82Updated last year
- A collection of reproducible inference engine benchmarksβ33Updated 4 months ago
- Official implementation for Training LLMs with MXFP4β91Updated 4 months ago
- PB-LLM: Partially Binarized Large Language Modelsβ153Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS β¦β60Updated 11 months ago
- β118Updated last year
- β202Updated 9 months ago
- β121Updated last year
- β120Updated last year
- Experiment of using Tangent to autodiff tritonβ81Updated last year