vedantroy / gpu_kernels
☆22Updated 8 months ago
Related projects: ⓘ
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆29Updated 6 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆50Updated 3 months ago
- ☆27Updated 3 weeks ago
- TensorRT LLM Benchmark Configuration☆10Updated last month
- ☆16Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆47Updated 2 weeks ago
- ☆83Updated 3 weeks ago
- ☆50Updated 3 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆36Updated 8 months ago
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆33Updated last year
- A minimal implementation of vllm.☆29Updated last month
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆58Updated this week
- ☆38Updated 9 months ago
- ☆30Updated 3 months ago
- JORA: JAX Tensor-Parallel LoRA Library (ACL 2024)☆28Updated 4 months ago
- Memory Optimizations for Deep Learning (ICML 2023)☆58Updated 6 months ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆72Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆134Updated 2 months ago
- Collection of kernels written in Triton language☆48Updated 2 weeks ago
- Simple and fast low-bit matmul kernels in CUDA☆48Updated this week
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆39Updated this week
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆25Updated last month
- ☆61Updated 3 weeks ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆55Updated this week
- ☆35Updated 10 months ago
- ☆66Updated 3 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 9 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆41Updated 3 weeks ago
- Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large …☆61Updated 2 years ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆57Updated 5 months ago