sgl-project / DeepGEMMLinks
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
☆18Updated this week
Alternatives and similar repositories for DeepGEMM
Users that are interested in DeepGEMM are comparing it to the libraries listed below
Sorting:
- ☆50Updated 3 months ago
- Quantized Attention on GPU☆44Updated 9 months ago
- Persistent dense gemm for Hopper in `CuTeDSL`☆15Updated 2 weeks ago
- ☆61Updated 4 months ago
- ☆91Updated last week
- ☆77Updated 3 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated 2 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆19Updated 3 weeks ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated last month
- ☆38Updated 3 weeks ago
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Updated 3 weeks ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆100Updated 3 months ago
- Benchmark tests supporting the TiledCUDA library.☆17Updated 9 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆67Updated this week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆19Updated this week
- Debug print operator for cudagraph debugging☆13Updated last year
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated 8 months ago
- ☆81Updated 7 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆18Updated 7 months ago
- ☆44Updated 3 weeks ago
- ☆11Updated 7 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆81Updated last week
- Odysseus: Playground of LLM Sequence Parallelism☆76Updated last year
- GPTQ inference TVM kernel☆40Updated last year
- A practical way of learning Swizzle☆25Updated 6 months ago
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆32Updated last week
- Standalone Flash Attention v2 kernel without libtorch dependency☆111Updated 11 months ago