pcg-mlp / KsanaLLM
☆328Updated 3 months ago
Alternatives and similar repositories for KsanaLLM:
Users that are interested in KsanaLLM are comparing it to the libraries listed below
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆715Updated 3 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆245Updated last week
- FlagScale is a large model toolkit based on open-sourced projects.☆269Updated this week
- GLake: optimizing GPU memory management and IO transmission.☆456Updated last month
- Disaggregated serving system for Large Language Models (LLMs).☆575Updated 3 weeks ago
- ☆127Updated 4 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆473Updated last year
- Materials for learning SGLang☆396Updated last week
- LLM Inference benchmark☆415Updated 9 months ago
- ☆139Updated last year
- Efficient and easy multi-instance LLM serving☆398Updated this week
- ☆131Updated 2 months ago
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated 2 years ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆99Updated last year
- FlagGems is an operator library for large language models implemented in Triton Language.☆510Updated this week
- ☆148Updated 3 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆343Updated 2 months ago
- Accelerate inference without tears☆313Updated last month
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆243Updated last year
- Transformer related optimization, including BERT, GPT☆59Updated last year
- Best practice for training LLaMA models in Megatron-LM☆650Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆360Updated 2 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆351Updated 2 weeks ago
- The road to hack SysML and become an system expert☆481Updated 7 months ago
- TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.☆94Updated 2 years ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆488Updated 2 weeks ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆53Updated 9 months ago
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆466Updated last week
- how to learn PyTorch and OneFlow☆427Updated last year
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆238Updated 2 weeks ago