DeepLink-org / deeplink.framework
☆56Updated last week
Related projects: ⓘ
- ☆68Updated 2 weeks ago
- ☆11Updated last week
- A benchmark suited especially for deep learning operators☆40Updated last year
- FlagGems is an operator library for large language models implemented in Triton Language.☆246Updated last week
- ☆133Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆186Updated last month
- A collection of memory efficient attention operators implemented in the Triton language.☆205Updated 3 months ago
- ☆140Updated 4 months ago
- ☆56Updated last week
- A fast communication-overlapping library for tensor parallelism on GPUs.☆184Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆265Updated this week
- flash attention tutorial written in python, triton, cuda, cutlass☆159Updated 3 months ago
- ☆70Updated 6 months ago
- ☆123Updated 3 months ago
- Development repository for the Triton-Linalg conversion☆137Updated last month
- Disaggregated serving system for Large Language Models (LLMs).☆278Updated last month
- learning how CUDA works☆150Updated last month
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆41Updated last month
- ☆95Updated 2 years ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆399Updated 2 weeks ago
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆266Updated last week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆276Updated last week
- This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit…☆227Updated this week
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆20Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆161Updated 2 months ago
- High performance Transformer implementation in C++.☆67Updated last week
- PyTorch distributed training acceleration framework☆16Updated this week
- Zero Bubble Pipeline Parallelism☆254Updated 2 weeks ago
- ☆90Updated 6 months ago
- ☆102Updated 3 months ago