volcengine / veScale
A PyTorch Native LLM Training Framework
☆797Updated 4 months ago
Alternatives and similar repositories for veScale:
Users that are interested in veScale are comparing it to the libraries listed below
- Disaggregated serving system for Large Language Models (LLMs).☆580Updated last month
- Distributed Triton for Parallel Systems☆644Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆912Updated 3 weeks ago
- Zero Bubble Pipeline Parallelism☆387Updated this week
- Efficient and easy multi-instance LLM serving☆402Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆805Updated last week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆364Updated 2 weeks ago
- GLake: optimizing GPU memory management and IO transmission.☆457Updated last month
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆450Updated 7 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆1,089Updated this week
- Materials for learning SGLang☆406Updated last week
- FlashInfer: Kernel Library for LLM Serving☆2,788Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆490Updated 2 weeks ago
- Ring attention implementation with flash attention☆759Updated last month
- Microsoft Automatic Mixed Precision Library☆596Updated 7 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆269Updated last week
- Latency and Memory Analysis of Transformer Models for Training and Inference☆409Updated 2 weeks ago
- Redis for LLMs☆951Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆715Updated 3 months ago
- A low-latency & high-throughput serving engine for LLMs☆351Updated 2 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆812Updated 8 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆663Updated 2 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆302Updated 5 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆266Updated 11 months ago
- ☆573Updated 2 months ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆820Updated this week
- Fast inference from large lauguage models via speculative decoding☆722Updated 8 months ago
- Perplexity GPU Kernels☆272Updated last week
- FlagGems is an operator library for large language models implemented in Triton Language.☆516Updated this week
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆714Updated this week