InternLM / turbomindLinks
☆92Updated 4 months ago
Alternatives and similar repositories for turbomind
Users that are interested in turbomind are comparing it to the libraries listed below
Sorting:
- ☆96Updated 10 months ago
- ⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA.🎉☆194Updated 2 months ago
- ☆60Updated 3 months ago
- ☆145Updated 5 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆137Updated 3 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆93Updated 2 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆111Updated 10 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated last month
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆39Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆106Updated 2 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆260Updated 2 weeks ago
- DeeperGEMM: crazy optimized version☆71Updated 2 months ago
- Fast and memory-efficient exact attention☆82Updated this week
- ☆78Updated 3 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆110Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆102Updated 3 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆318Updated last year
- ☆195Updated 2 months ago
- ☆75Updated 2 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆154Updated last month
- ☆31Updated 6 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆74Updated 11 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- ☆89Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆273Updated last year
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆193Updated this week
- Implement Flash Attention using Cute.☆92Updated 7 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- ☆76Updated 8 months ago