lix19937 / llm-deployLinks
AI Infra LLM infer/ tensorrt-llm/ vllm
☆20Updated 5 months ago
Alternatives and similar repositories for llm-deploy
Users that are interested in llm-deploy are comparing it to the libraries listed below
Sorting:
- ☆148Updated 4 months ago
- ☆139Updated last year
- ☆127Updated 5 months ago
- A tutorial for CUDA&PyTorch☆142Updated 4 months ago
- Tutorials for writing high-performance GPU operators in AI frameworks.☆130Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆92Updated last week
- 分层解耦的深度学习推理引擎☆73Updated 3 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆37Updated 3 months ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆57Updated 6 months ago
- Collection of blogs on AI development☆19Updated 6 months ago
- ☆58Updated 6 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆100Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆79Updated 3 weeks ago
- ☆96Updated 8 months ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆48Updated last year
- Implement custom operators in PyTorch with cuda/c++☆62Updated 2 years ago
- ☆134Updated last year
- ☆29Updated 4 months ago
- ☆21Updated 4 years ago
- Standalone Flash Attention v2 kernel without libtorch dependency☆110Updated 8 months ago
- Transformer related optimization, including BERT, GPT☆17Updated last year
- ☆93Updated 2 months ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆41Updated 9 months ago
- Optimize softmax in triton in many cases☆21Updated 9 months ago
- Examples of CUDA implementations by Cutlass CuTe☆190Updated 4 months ago
- Triton Compiler related materials.☆29Updated 5 months ago
- Benchmark code for the "Online normalizer calculation for softmax" paper☆94Updated 6 years ago
- ☆73Updated 3 weeks ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆68Updated 9 months ago
- ☆96Updated 3 years ago