This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
☆43Aug 14, 2024Updated last year
Alternatives and similar repositories for FastGen
Users that are interested in FastGen are comparing it to the libraries listed below
Sorting:
- ☆14Jun 4, 2024Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆48Jun 19, 2024Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆149Aug 9, 2024Updated last year
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆57Mar 26, 2024Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆376Jul 10, 2025Updated 8 months ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated last year
- ☆306Jul 10, 2025Updated 8 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆408Aug 13, 2024Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆506Aug 1, 2024Updated last year
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆11Jun 18, 2024Updated last year
- ☆52May 13, 2024Updated last year
- This repository contains the code for the paper: SirLLM: Streaming Infinite Retentive LLM☆60May 28, 2024Updated last year
- Inverse Scaling in Test-Time Compute☆25Dec 3, 2025Updated 3 months ago
- WIPE implementation☆13Nov 26, 2023Updated 2 years ago
- ☆15Apr 11, 2024Updated last year
- Explore Inter-layer Expert Affinity in MoE Model Inference☆16May 6, 2024Updated last year
- ☆36Oct 10, 2024Updated last year
- ☆28Dec 2, 2024Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆359Nov 20, 2025Updated 4 months ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆18Oct 21, 2024Updated last year
- Official implementation for "Mixture of In-Context Experts Enhance LLMs’ Awareness of Long Contexts" (Accepted by Neurips2024)☆13Jan 7, 2025Updated last year
- ACL 2023☆39Jun 6, 2023Updated 2 years ago
- ☆21Feb 5, 2024Updated 2 years ago
- ☆52Nov 5, 2024Updated last year
- [NAACL'25 🏆 SAC Award] Official code for "Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert…☆16Feb 4, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆54Mar 27, 2024Updated last year
- Compressed LLMs for Efficient Text Generation [ICLR'24 Workshop]☆90Sep 13, 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
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆134May 16, 2024Updated last year
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆73Mar 25, 2025Updated 11 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆172Nov 26, 2025Updated 3 months ago
- ☆19Oct 14, 2024Updated last year
- [EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study un…☆17Dec 17, 2025Updated 3 months ago
- ☆47Nov 25, 2024Updated last year
- High Performance FP8 GEMM Kernels for SM89 and later GPUs.☆20Jan 24, 2025Updated last year
- ☆20Sep 24, 2025Updated 5 months ago
- ☆85Apr 18, 2025Updated 11 months ago
- ☆82Apr 1, 2024Updated last year