gogongxt / nano-sglangLinks
☆41Updated last month
Alternatives and similar repositories for nano-sglang
Users that are interested in nano-sglang are comparing it to the libraries listed below
Sorting:
- ☆97Updated 7 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆42Updated 8 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆45Updated 5 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆127Updated 6 months ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆229Updated 3 months ago
- ☆102Updated last year
- ☆151Updated 8 months ago
- Implement Flash Attention using Cute.☆96Updated 11 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Updated 2 months ago
- ☆81Updated 7 months ago
- A simple calculation for LLM MFU.☆50Updated 2 months ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆112Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆107Updated 7 months ago
- ☆65Updated 6 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆78Updated last year
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆115Updated 6 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆119Updated last year
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- ☆121Updated 3 months ago
- ☆111Updated 6 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆82Updated this week
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆82Updated this week
- A Triton JIT runtime and ffi provider in C++☆29Updated 2 weeks ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆62Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆143Updated 2 months ago
- DeeperGEMM: crazy optimized version☆73Updated 6 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆189Updated 9 months ago
- A lightweight design for computation-communication overlap.☆187Updated last month
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆146Updated 3 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆52Updated last year