taishan1994 / LLM-QuantizationLinks
记录量化LLM中的总结。
☆33Updated 2 weeks ago
Alternatives and similar repositories for LLM-Quantization
Users that are interested in LLM-Quantization are comparing it to the libraries listed below
Sorting:
- TensorRT-in-Action 是一个 GitHub 代码库,提供了使用 TensorRT 的代码示例,并有对应 Jupyter Notebook。☆15Updated 2 years ago
- A light llama-like llm inference framework based on the triton kernel.☆153Updated 2 weeks ago
- 一个轻量化的大模型推理框架☆20Updated 4 months ago
- 使用 CUDA C++ 实现的 llama 模型推理框架☆62Updated 10 months ago
- A tutorial for CUDA&PyTorch☆156Updated 8 months ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆10Updated last year
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆108Updated 2 months ago
- ☆26Updated 2 years ago
- This is a repository to practice multi-thread programming in C++☆26Updated last year
- ☆59Updated 10 months ago
- A tool for model sparse based on torch.fx☆13Updated last year
- ☆36Updated 4 months ago
- 机器学习编译 陈天奇☆45Updated 2 years ago
- ☆139Updated last year
- Quick and Self-Contained TensorRT Custom Plugin Implementation and Integration☆71Updated 4 months ago
- 该代码与B站上的视频 https://www.bilibili.com/video/BV18L41197Uz/?spm_id_from=333.788&vd_source=eefa4b6e337f16d87d87c2c357db8ca7 相关联。☆70Updated 2 years ago
- 使用 cutlass 实现 flash-attention 精简版,具有教学意义☆49Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆75Updated last year
- Awesome code, projects, books, etc. related to CUDA☆24Updated last month
- Llama3 Streaming Chat Sample☆22Updated last year
- Optimize softmax in triton in many cases☆21Updated last year
- ☆42Updated 3 years ago
- ☆43Updated last year
- An onnx-based quantitation tool.☆71Updated last year
- ☆25Updated last month
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆50Updated last year
- llm deploy project based onnx.☆44Updated 11 months ago
- ☆56Updated 2 months ago
- Tutorials of Extending and importing TVM with CMAKE Include dependency.☆14Updated 11 months ago
- ☆32Updated 8 months ago