BBuf / megatron-lm-parallel-group-playgroundLinks
☆16Updated last year
Alternatives and similar repositories for megatron-lm-parallel-group-playground
Users that are interested in megatron-lm-parallel-group-playground are comparing it to the libraries listed below
Sorting:
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated 2 weeks ago
- Quantized Attention on GPU☆44Updated 7 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- ☆79Updated last year
- ☆86Updated 3 months ago
- ☆60Updated 2 months ago
- OneFlow Serving☆20Updated 2 months ago
- ☆49Updated last month
- ☆11Updated last year
- GPTQ inference TVM kernel☆40Updated last year
- ☆114Updated 3 weeks ago
- ☆31Updated last year
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆133Updated last year
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆53Updated 7 months ago
- Estimate MFU for DeepSeekV3☆24Updated 5 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆16Updated last year
- Vocabulary Parallelism☆19Updated 3 months ago
- A simple calculation for LLM MFU.☆38Updated 3 months ago
- 🤗CacheDiT: A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers🔥☆61Updated this week
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated 11 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆71Updated 10 months ago
- ☆77Updated 2 months ago
- ☆71Updated last month
- ☆96Updated 9 months ago
- Transformer related optimization, including BERT, GPT☆17Updated last year
- DeeperGEMM: crazy optimized version☆69Updated last month
- ☆22Updated last year
- A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.☆13Updated 2 years ago