FMInference / DejaVu
☆314Updated 10 months ago
Alternatives and similar repositories for DejaVu:
Users that are interested in DejaVu are comparing it to the libraries listed below
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆294Updated 7 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆420Updated 6 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆496Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆223Updated 3 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆339Updated 2 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆272Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆332Updated 6 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆391Updated 5 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆244Updated 2 months ago
- ☆219Updated 9 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆424Updated this week
- Explorations into some recent techniques surrounding speculative decoding☆239Updated last month
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆269Updated 5 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆205Updated 6 months ago
- This repository contains integer operators on GPUs for PyTorch.☆191Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆290Updated last week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆160Updated last week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆234Updated 3 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆199Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆296Updated 2 weeks ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆388Updated 3 months ago
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆595Updated this week
- Microsoft Automatic Mixed Precision Library☆566Updated 4 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆192Updated 2 months ago
- A low-latency & high-throughput serving engine for LLMs☆310Updated 2 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆237Updated 8 months ago
- Zero Bubble Pipeline Parallelism☆336Updated last week
- Ring attention implementation with flash attention☆674Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 7 months ago
- Fast inference from large lauguage models via speculative decoding☆657Updated 5 months ago