#Kv-cache

Showing 19 of 19 repositories tagged #kv-cache, ranked by stars

LMCache
LMCache
LMCache

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Score
0
★ 10.4k ⑂ 1.5k +115/day
Python
HDT3213
HDT3213
godis

A Golang implemented Redis Server and Cluster. Go 语言实现的 Redis 服务器和分布式集群

Score
0
★ 3.8k ⑂ 601
Go
Zefan-Cai
Zefan-Cai
KVCache-Factory

Unified KV Cache Compression Methods for Auto-Regressive Models

Score
100
★ 1.4k ⑂ 177
Python
NVIDIA
NVIDIA
kvpress

LLM KV cache compression made easy

Score
92
★ 1.1k ⑂ 157 +4/day
Python
harleyszhang
harleyszhang
llm_note

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

Score
85
★ 882 ⑂ 88
Python
raymin0223
raymin0223
mixture_of_recursions

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)

Score
46
★ 579 ⑂ 84
Python
openinfer-project
openinfer-project
openinfer

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Score
100
★ 526 ⑂ 75 +5/day
Rust
zengxiao-he
zengxiao-he
tessera

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

Score
50
★ 512 ⑂ 5 +24/day
Python
Zefan-Cai
Zefan-Cai
Awesome-LLM-KV-Cache

Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

Score
77
★ 456 ⑂ 28 +3/day
huawei-csl
huawei-csl
KVarN

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

Score
69
★ 434 ⑂ 28 +4/day
Python
thu-nics
thu-nics
C2C

[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

Score
54
★ 417 ⑂ 52 +3/day
Python
quantumaikr
quantumaikr
quant.cpp

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

Score
62
★ 395 ⑂ 43
C
dipampaul17
dipampaul17
KVSplit

Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.

Score
23
★ 361 ⑂ 13
Python
feichai0017
feichai0017
quillcache

Distributed KV cache pool + control plane for LLM serving

Score
0
★ 184 ⑂ 18 +1/day
Rust
kddubey
kddubey
cappr

Completion After Prompt Probability. Make your LLM make a choice

Score
0
★ 82 ⑂ 3
Python
aju22
aju22
LLaMA2

This repository contains an implementation of the LLaMA 2 (Large Language Model Meta AI) model, a Generative Pretrained Transformer (GPT) variant. The implementation focuses on the model architecture and the inference process. The code is restructured and heavily commented to facilitate easy understanding of the key parts of the architecture.

Score
8
★ 75 ⑂ 7
Python
OnlyTerp
OnlyTerp
turboquant

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

Score
38
★ 75 ⑂ 11
Python
VectifyAI
VectifyAI
ConDB

ConDB: The KV-Cache Native Context Database

Score
31
★ 43 ⑂ 7 +3/day
Python
pleasedodisturb
pleasedodisturb
awesome-llm-token-optimization

A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

Score
15
★ 21 ⑂ 6 +6/day
Related Topics
#llm#llm-inference#vllm#quantization#pytorch#kv-cache-compression#cuda#inference#long-context#rust#transformer#ai

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly