BBuf / tensorrt-llm-moeLinks
☆34Updated last year
Alternatives and similar repositories for tensorrt-llm-moe
Users that are interested in tensorrt-llm-moe are comparing it to the libraries listed below
Sorting:
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆148Updated 8 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆78Updated last year
- Standalone Flash Attention v2 kernel without libtorch dependency☆113Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Updated 4 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆46Updated 7 months ago
- ☆61Updated 6 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Updated 6 months ago
- ☆65Updated 9 months ago
- ☆105Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆44Updated 11 months ago
- Implement Flash Attention using Cute.☆100Updated last year
- A Triton JIT runtime and ffi provider in C++☆30Updated last week
- ☆96Updated 10 months ago
- ☆49Updated last year
- ☆14Updated 3 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆92Updated last week
- ☆112Updated 8 months ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆71Updated last year
- ☆152Updated last year
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆248Updated 2 weeks ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆105Updated this week
- DeeperGEMM: crazy optimized version☆73Updated 8 months ago
- FlagCX is a scalable and adaptive cross-chip communication library.☆170Updated this week
- Tutorials of Extending and importing TVM with CMAKE Include dependency.☆16Updated last year
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆192Updated last year
- 使用 cutlass 实现 flash-attention 精简版，具有教学意义☆54Updated last year
- CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API☆35Updated 2 years ago
- llama INT4 cuda inference with AWQ☆55Updated last year
- A practical way of learning Swizzle☆36Updated last year
- 使用 CUDA C++ 实现的 llama 模型推理框架☆64Updated last year