vllm-project / compressed-tensorsLinks
A safetensors extension to efficiently store sparse quantized tensors on disk
☆171Updated this week
Alternatives and similar repositories for compressed-tensors
Users that are interested in compressed-tensors are comparing it to the libraries listed below
Sorting:
- ☆201Updated 5 months ago
- Fast low-bit matmul kernels in Triton☆381Updated 2 weeks ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆83Updated last year
- Applied AI experiments and examples for PyTorch☆299Updated last month
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆215Updated this week
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 3 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆266Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆143Updated last month
- Efficient LLM Inference over Long Sequences☆390Updated 3 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆237Updated 11 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆386Updated last year
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆258Updated this week
- PyTorch bindings for CUTLASS grouped GEMM.☆124Updated 4 months ago
- Cataloging released Triton kernels.☆261Updated last month
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- ☆152Updated 3 months ago
- This repository contains the experimental PyTorch native float8 training UX☆223Updated last year
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- Code for data-aware compression of DeepSeek models☆56Updated 4 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆246Updated last week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆114Updated 2 weeks ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆270Updated 2 months ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆278Updated this week
- Collection of kernels written in Triton language☆156Updated 6 months ago
- ☆240Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 10 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆244Updated 2 weeks ago
- ☆129Updated 4 months ago
- ☆72Updated 6 months ago