AlibabaResearch / flash-llmLinks
Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
☆221Updated 2 years ago
Alternatives and similar repositories for flash-llm
Users that are interested in flash-llm are comparing it to the libraries listed below
Sorting:
- ☆153Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆124Updated 4 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- ☆100Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last month
- A lightweight design for computation-communication overlap.☆181Updated 2 weeks ago
- ☆341Updated last year
- ☆59Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆252Updated last week
- ☆74Updated last week
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆67Updated 7 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆154Updated 2 weeks ago
- ☆78Updated 6 months ago
- ☆124Updated 11 months ago
- ☆87Updated 3 years ago
- This repository contains integer operators on GPUs for PyTorch.☆219Updated 2 years ago
- ☆240Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.