neuralmagic / compressed-tensors
A safetensors extension to efficiently store sparse quantized tensors on disk
☆51Updated this week
Related projects ⓘ
Alternatives and complementary repositories for compressed-tensors
- Simple and fast low-bit matmul kernels in CUDA / Triton☆147Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- Applied AI experiments and examples for PyTorch☆168Updated 3 weeks ago
- ☆47Updated 2 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆112Updated 8 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆38Updated 10 months ago
- extensible collectives library in triton☆72Updated 2 months ago
- ☆55Updated 6 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated last week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆90Updated 4 months ago
- ☆88Updated 2 months ago
- Fast Inference of MoE Models with CPU-GPU Orchestration☆173Updated this week
- Cataloging released Triton kernels.☆138Updated 2 months ago
- ring-attention experiments☆97Updated last month
- ☆96Updated 2 months ago
- This repository contains the experimental PyTorch native float8 training UX☆212Updated 3 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆185Updated last month
- ☆153Updated this week
- LLM KV cache compression made easy☆168Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆149Updated 4 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆211Updated 3 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆253Updated last month
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆87Updated last month
- KV cache compression for high-throughput LLM inference☆87Updated this week
- ☆45Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆203Updated 3 weeks ago