[ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
☆144Dec 4, 2024Updated last year
Alternatives and similar repositories for MagicDec
Users that are interested in MagicDec are comparing it to the libraries listed below
Sorting:
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆277Aug 31, 2024Updated last year
- 16-fold memory access reduction with nearly no loss☆108Mar 26, 2025Updated 11 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆376Jul 10, 2025Updated 8 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆359Nov 20, 2025Updated 3 months ago
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆57Mar 26, 2024Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆531Feb 10, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆818Mar 6, 2025Updated last year
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆33Nov 29, 2024Updated last year
- ☆28May 24, 2025Updated 9 months ago
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,196Mar 9, 2026Updated last week
- ☆306Jul 10, 2025Updated 8 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆335Jul 2, 2024Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆180Jul 12, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆949Oct 29, 2025Updated 4 months ago
- scalable and robust tree-based speculative decoding algorithm☆372Jan 28, 2025Updated last year
- ☆64Dec 3, 2024Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆408Aug 13, 2024Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Apr 7, 2025Updated 11 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆506Aug 1, 2024Updated last year
- A sparse attention kernel supporting mix sparse patterns☆480Jan 18, 2026Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆79Jun 17, 2024Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,220Feb 20, 2026Updated last month
- ☆65Apr 26, 2025Updated 10 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆51Oct 18, 2024Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆215Mar 5, 2026Updated 2 weeks ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆281Mar 6, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,041Sep 4, 2024Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆164Oct 13, 2025Updated 5 months ago
- Fast low-bit matmul kernels in Triton☆438Feb 1, 2026Updated last month
- A parallelism VAE avoids OOM for high resolution image generation☆89Mar 12, 2026Updated last week
- ☆13Dec 9, 2024Updated last year
- ☆87Oct 17, 2025Updated 5 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆261Nov 18, 2024Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆668Feb 24, 2026Updated 3 weeks ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆74Jul 14, 2025Updated 8 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆54Mar 27, 2024Updated last year
- A low-latency & high-throughput serving engine for LLMs☆484Jan 8, 2026Updated 2 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆752Aug 6, 2025Updated 7 months ago