DeepLink-org / dlinfer
☆43Updated this week
Alternatives and similar repositories for dlinfer:
Users that are interested in dlinfer are comparing it to the libraries listed below
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆237Updated this week
- ☆127Updated 2 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆246Updated this week
- ☆78Updated last year
- ☆139Updated 10 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆93Updated last year
- ☆120Updated last week
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆363Updated this week
- Built upon Megatron-Deepspeed and HuggingFace Trainer, EasyLLM has reorganized the code logic with a focus on usability. While enhancing …☆46Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆103Updated 2 months ago
- ☆156Updated this week
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆107Updated 3 weeks ago
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- ☆38Updated 4 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆322Updated 3 weeks ago
- An industrial extension library of pytorch to accelerate large scale model training☆25Updated last month
- ☆74Updated 3 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆445Updated 3 weeks ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- ☆66Updated 4 months ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆58Updated 2 months ago
- ☆179Updated 5 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆51Updated 7 months ago
- ☆319Updated last month
- An easy-to-use package for implementing SmoothQuant for LLMs☆94Updated 9 months ago
- ☆58Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆250Updated 9 months ago
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆79Updated 2 months ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆237Updated 11 months ago