fw-ai / llama-cuda-graph-example
Example of applying CUDA graphs to LLaMA-v2
☆10Updated last year
Related projects ⓘ
Alternatives and complementary repositories for llama-cuda-graph-example
- Make triton easier☆41Updated 5 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆38Updated 10 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆51Updated this week
- ☆55Updated 6 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated last week
- ring-attention experiments☆97Updated last month
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆66Updated 5 months ago
- ☆101Updated last month
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- Hydragen: High-Throughput LLM Inference with Shared Prefixes☆25Updated 6 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆56Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated 3 weeks ago
- Packages and instructions for training and inference of LLMs on NVIDIA's new GH200 machines☆19Updated 2 months ago
- FlexAttention w/ FlashAttention3 Support☆27Updated last month
- extensible collectives library in triton☆72Updated 2 months ago
- Experiment of using Tangent to autodiff triton☆72Updated 10 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- Transformers components but in Triton☆27Updated last week
- ☆44Updated 11 months ago
- ☆20Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆57Updated 5 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆87Updated 3 months ago
- ☆96Updated 2 months ago
- Materials for learning SGLang☆110Updated this week
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆30Updated 3 months ago
- Applied AI experiments and examples for PyTorch☆168Updated 3 weeks ago
- ☆90Updated 2 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated last week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆20Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week