vllm-project / tpu-inferenceLinks
TPU inference for vLLM, with unified JAX and PyTorch support.
☆207Updated this week
Alternatives and similar repositories for tpu-inference
Users that are interested in tpu-inference are comparing it to the libraries listed below
Sorting:
- Ship correct and fast LLM kernels to PyTorch☆130Updated this week
- Fast low-bit matmul kernels in Triton☆418Updated 3 weeks ago
- Applied AI experiments and examples for PyTorch☆312Updated 4 months ago
- ☆270Updated last week
- extensible collectives library in triton☆91Updated 9 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆139Updated 7 months ago
- PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"☆79Updated 3 weeks ago
- ring-attention experiments☆161Updated last year
- Load compute kernels from the Hub☆359Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆308Updated this week
- Cataloging released Triton kernels.☆282Updated 4 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆218Updated this week
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆159Updated 2 months ago
- JAX backend for SGL☆211Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆522Updated last week
- Collection of kernels written in Triton language☆174Updated 9 months ago
- ☆100Updated last year
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆278Updated last month
- Boosting 4-bit inference kernels with 2:4 Sparsity☆90Updated last year
- This repository contains the experimental PyTorch native float8 training UX☆227Updated last year
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆247Updated 8 months ago
- torchcomms: a modern PyTorch communications API☆319Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆259Updated 3 months ago
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆182Updated last week
- Triton-based Symmetric Memory operators and examples☆72Updated 2 months ago
- JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs wel…☆398Updated last week
- A Quirky Assortment of CuTe Kernels☆741Updated this week
- Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)☆467Updated 2 weeks ago
- Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Lar…☆91Updated this week
- ☆219Updated 11 months ago