deepspeedai / DeepSpeed-KernelsLinks
☆72Updated 2 months ago
Alternatives and similar repositories for DeepSpeed-Kernels
Users that are interested in DeepSpeed-Kernels are comparing it to the libraries listed below
Sorting:
- ☆105Updated 9 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆79Updated 9 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- extensible collectives library in triton☆86Updated 2 months ago
- ☆81Updated 7 months ago
- A Python library transfers PyTorch tensors between CPU and NVMe☆116Updated 6 months ago
- ☆63Updated this week
- ☆86Updated 2 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆136Updated this week
- PyTorch bindings for CUTLASS grouped GEMM.☆99Updated 3 weeks ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆109Updated 11 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- ☆60Updated last month
- Framework to reduce autotune overhead to zero for well known deployments.☆77Updated this week
- ☆71Updated last month
- ☆75Updated 5 months ago
- ☆91Updated 5 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆126Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆252Updated 7 months ago
- llama INT4 cuda inference with AWQ☆54Updated 5 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 7 months ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆94Updated 6 years ago
- ☆38Updated this week
- ☆96Updated 9 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- GPTQ inference TVM kernel☆40Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆90Updated 2 weeks ago
- Vocabulary Parallelism☆19Updated 3 months ago
- Fast low-bit matmul kernels in Triton☆322Updated this week