void-main / FasterTransformerLinks
Transformer related optimization, including BERT, GPT
☆59Updated 2 years ago
Alternatives and similar repositories for FasterTransformer
Users that are interested in FasterTransformer are comparing it to the libraries listed below
Sorting:
- ☆129Updated 9 months ago
- ☆139Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆479Updated last year
- Running BERT without Padding☆475Updated 3 years ago
- ☆79Updated last year
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆107Updated 6 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆41Updated 7 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆282Updated last year
- ☆148Updated 7 months ago
- ☆150Updated 9 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆154Updated last week
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆65Updated last year
- ☆21Updated 2 years ago
- export llama to onnx☆136Updated 9 months ago
- ☆205Updated 5 months ago
- Simple Dynamic Batching Inference☆145Updated 3 years ago
- ☆100Updated last year
- ☆219Updated 2 years ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆317Updated 7 months ago
- ☆121Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆144Updated 2 months ago
- ☆59Updated 11 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆266Updated 2 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆362Updated this week
- Zero Bubble Pipeline Parallelism☆432Updated 5 months ago
- A quantization algorithm for LLM☆143Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆576Updated last week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆892Updated this week
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated last month