vllm-project / vllm-nccl
Manages vllm-nccl dependency
☆17Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for vllm-nccl
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆24Updated 2 weeks ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆34Updated 8 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆57Updated 5 months ago
- ☆42Updated 6 months ago
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆57Updated last year
- GPTQ inference TVM kernel☆36Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- vLLM performance dashboard☆18Updated 6 months ago
- ☆18Updated last week
- Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.☆25Updated 2 weeks ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆75Updated 8 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆34Updated 10 months ago
- Transformer related optimization, including BERT, GPT☆17Updated last year
- Distributed IO-aware Attention algorithm☆17Updated 3 months ago
- Materials for learning SGLang☆105Updated this week
- Elixir: Train a Large Language Model on a Small GPU Cluster☆13Updated last year
- Transformers components but in Triton☆27Updated this week
- ☆64Updated 3 months ago
- Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…☆52Updated last week
- 使用 CUDA C++ 实现的 llama 模型推理框架☆24Updated 2 weeks ago
- Benchmark for machine learning model online serving (LLM, embedding, Stable-Diffusion, Whisper)☆27Updated last year
- The official code for paper "parallel speculative decoding with adaptive draft length."☆24Updated 2 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆38Updated last month
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆52Updated 7 months ago
- ☆22Updated 11 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 11 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆82Updated 8 months ago
- Longitudinal Evaluation of LLMs via Data Compression☆26Updated 5 months ago
- ☆23Updated last year