Yard1 / Ray-DeepSpeed-Inference
☆18Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Ray-DeepSpeed-Inference
- A simple service that integrates vLLM with Ray Serve for fast and scalable LLM serving.☆54Updated 7 months ago
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆74Updated 10 months ago
- ☆158Updated last month
- Benchmark suite for LLMs from Fireworks.ai☆58Updated 2 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆130Updated 4 months ago
- fastertransformer for codegeex model☆64Updated last year
- A flexible and efficient training framework for large-scale alignment tasks☆209Updated this week
- A LLaMA1/LLaMA12 Megatron implement.☆27Updated 11 months ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆236Updated 8 months ago
- This is a text generation method which returns a generator, streaming out each token in real-time during inference, based on Huggingface/…☆96Updated 8 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆82Updated 8 months ago
- Evaluation for AI apps and agent☆35Updated 10 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆126Updated 5 months ago
- ☆53Updated 5 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆112Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆76Updated last month
- AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark☆106Updated last month
- ☆35Updated this week
- A pipeline for LLM knowledge distillation☆78Updated 3 months ago
- Expert Specialized Fine-Tuning☆145Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆176Updated this week
- ☆111Updated 8 months ago
- KV cache compression for high-throughput LLM inference☆87Updated this week
- Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper☆124Updated 4 months ago
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆220Updated 3 weeks ago
- Data preparation code for CrystalCoder 7B LLM☆42Updated 6 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆285Updated last month
- OpenAI compatible API for TensorRT LLM triton backend☆177Updated 3 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆89Updated last year
- Reformatted Alignment☆112Updated last month