feifeibear / LLMSpeculativeSampling
Fast inference from large lauguage models via speculative decoding
β562Updated 2 months ago
Related projects β
Alternatives and complementary repositories for LLMSpeculativeSampling
- π° Must-read papers and blogs on Speculative Decoding β‘οΈβ447Updated this week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.β387Updated 3 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)β184Updated 2 weeks ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)β815Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inferenceβ352Updated last week
- β283Updated 7 months ago
- Ring attention implementation with flash attentionβ578Updated this week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningβ553Updated 8 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decodingβ1,143Updated 3 weeks ago
- Explorations into some recent techniques surrounding speculative decodingβ209Updated last year
- [ACL 2024] LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingβ657Updated last month
- Best practice for training LLaMA models in Megatron-LMβ627Updated 10 months ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarksβ253Updated 3 months ago
- β·οΈ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)β880Updated 4 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Servingβ433Updated 2 months ago
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichβ¦β863Updated last month
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Vβ¦β315Updated this week
- FlashInfer: Kernel Library for LLM Servingβ1,395Updated this week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline modβ¦β310Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024β172Updated last month
- Disaggregated serving system for Large Language Models (LLMs).β348Updated 2 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationβ302Updated 2 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**β135Updated 5 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Servingβ277Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.β611Updated 2 months ago
- Awesome LLM compression research papers and tools.β1,174Updated this week
- [NeurIPS'24 Spotlight] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inβ¦β776Updated this week
- β499Updated 2 months ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"β253Updated 2 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.β278Updated 3 months ago