void-main / fastertransformer_backendLinks
☆21Updated 2 years ago
Alternatives and similar repositories for fastertransformer_backend
Users that are interested in fastertransformer_backend are comparing it to the libraries listed below
Sorting:
- Transformer related optimization, including BERT, GPT☆59Updated 2 years ago
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- ☆129Updated 10 months ago
- Running BERT without Padding☆475Updated 3 years ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆479Updated last year
- LLM Inference benchmark☆428Updated last year
- ☆139Updated last year
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆266Updated 2 months ago
- ☆413Updated last year
- ☆219Updated 2 years ago
- ☆205Updated 5 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆903Updated this week
- A flexible and efficient training framework for large-scale alignment tasks☆433Updated this week
- ☆508Updated last month
- Best practice for training LLaMA models in Megatron-LM☆659Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆68Updated 2 years ago
- ☆79Updated last year
- ☆121Updated last year
- FlagScale is a large model toolkit based on open-sourced projects.☆364Updated this week
- export llama to onnx☆136Updated 9 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆269Updated 2 years ago
- ☆84Updated 2 years ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆98Updated last year
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆66Updated last year
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆248Updated last year
- Accelerate inference without tears☆361Updated last week
- The Triton TensorRT-LLM Backend☆903Updated this week
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆224Updated last year
- ☆148Updated 7 months ago
- A LLaMA1/LLaMA12 Megatron implement.☆28Updated last year