FMInference / H2OLinks
[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
☆473Updated last year
Alternatives and similar repositories for H2O
Users that are interested in H2O are comparing it to the libraries listed below
Sorting:
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆311Updated 4 months ago
- ☆335Updated last year
- ☆278Updated 2 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆333Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆201Updated 7 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆323Updated 7 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆377Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆531Updated last month
- Fast inference from large lauguage models via speculative decoding☆815Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆111Updated 5 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆207Updated this week
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆312Updated 6 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆454Updated 4 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆547Updated last year
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆45Updated 6 months ago
- Awesome list for LLM pruning.☆257Updated last week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆216Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆239Updated last month
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆490Updated 7 months ago
- ☆147Updated 6 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆138Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 5 months ago
- ☆55Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆562Updated last week
- Explorations into some recent techniques surrounding speculative decoding☆285Updated 8 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆374Updated last week