feifeibear / LLMSpeculativeSampling
Fast inference from large lauguage models via speculative decoding
☆630Updated 4 months ago
Alternatives and similar repositories for LLMSpeculativeSampling:
Users that are interested in LLMSpeculativeSampling are comparing it to the libraries listed below
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆558Updated this week
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆912Updated 2 weeks ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆416Updated 5 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆213Updated 2 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆578Updated 10 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆400Updated 2 weeks ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,179Updated 3 months ago
- ☆310Updated 9 months ago
- LongBench v2 and LongBench (ACL 2024)☆755Updated this week
- veRL: Volcano Engine Reinforcement Learning for LLM☆690Updated this week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆373Updated 4 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆186Updated last month
- Best practice for training LLaMA models in Megatron-LM☆638Updated last year
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆908Updated last month
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆928Updated 3 months ago
- Explorations into some recent techniques surrounding speculative decoding☆229Updated 3 weeks ago
- Ring attention implementation with flash attention☆645Updated 3 weeks ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆521Updated 2 weeks ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆151Updated 7 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆680Updated 4 months ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆255Updated 5 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆687Updated 3 months ago
- ☆525Updated 4 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆438Updated 4 months ago
- Scalable toolkit for efficient model alignment☆674Updated this week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆481Updated 2 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆377Updated 3 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆369Updated 2 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆303Updated 3 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆256Updated this week