Skip to content

winkay2000/llama-cpp-turboquant

BranchesTags
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8,856 Commits
.devops
.devops
 
 
.gemini
.gemini
 
 
.github
.github
 
 
benches
benches
 
 
ci
ci
 
 
cmake
cmake
 
 
codebooks
codebooks
 
 
common
common
 
 
docs
docs
 
 
examples
examples
 
 
ggml
ggml
 
 
gguf-py
gguf-py
 
 
grammars
grammars
 
 
include
include
 
 
licenses
licenses
 
 
media
media
 
 
models
models
 
 
pocs
pocs
 
 
requirements
requirements
 
 
scripts
scripts
 
 
src
src
 
 
tests
tests
 
 
tools
tools
 
 
vendor
vendor
 
 
.clang-format
.clang-format
 
 
.clang-tidy
.clang-tidy
 
 
.dockerignore
.dockerignore
 
 
.ecrc
.ecrc
 
 
.editorconfig
.editorconfig
 
 
.flake8
.flake8
 
 
.gitattributes
.gitattributes
 
 
.gitignore
.gitignore
 
 
.gitmodules
.gitmodules
 
 
.pre-commit-config.yaml
.pre-commit-config.yaml
 
 
AUTHORS
AUTHORS
 
 
CMakeLists.txt
CMakeLists.txt
 
 
CMakePresets.json
CMakePresets.json
 
 
CODEOWNERS
CODEOWNERS
 
 
CONTRIBUTING.md
CONTRIBUTING.md
 
 
LICENSE
LICENSE
 
 
Makefile
Makefile
 
 
README.md
README.md
 
 
SECURITY.md
SECURITY.md
 
 
apply_turbo_cuda_v2.py
apply_turbo_cuda_v2.py
 
 
build-xcframework.sh
build-xcframework.sh
 
 
buunslamma.png
buunslamma.png
 
 
convert_hf_to_gguf.py
convert_hf_to_gguf.py
 
 
convert_hf_to_gguf_update.py
convert_hf_to_gguf_update.py
 
 
convert_llama_ggml_to_gguf.py
convert_llama_ggml_to_gguf.py
 
 
convert_lora_to_gguf.py
convert_lora_to_gguf.py
 
 
flake.lock
flake.lock
 
 
flake.nix
flake.nix
 
 
mypy.ini
mypy.ini
 
 
poetry.lock
poetry.lock
 
 
pyproject.toml
pyproject.toml
 
 
pyrightconfig.json
pyrightconfig.json
 
 
requirements.txt
requirements.txt
 
 
servers
servers
 
 
ty.toml
ty.toml
 
 

Repository files navigation

buun-llama-cpp

buunslamma

This is a highly experimental fork of llama.cpp. Use at your own discretion.

A fork of llama.cpp with Trellis-Coded Quantization (TCQ) for KV cache compression. 2-3x more context in the same VRAM, with quality that matches or beats FP16.

Paper: Closing the Gap: Trellis-Coded Quantization for KV Cache at 2-3 Bits

What is TCQ?

Standard KV cache quantization treats each value independently. TCQ constrains quantization indices to follow a 512-state trellis, enabling a much larger effective codebook at the same bit rate. Combined with FWHT rotation and context-adaptive norm scaling, this achieves 10-44% KL-divergence reduction over scalar quantization at 2-3 bits per value.

At 3.25 bits per value, TCQ produces lower perplexity than FP16 KV cache (5.802 vs 5.805).

Build

cmake -B build \
  -DGGML_CUDA=ON \
  -DGGML_NATIVE=ON \
  -DGGML_CUDA_FA=ON \
  -DGGML_CUDA_FA_ALL_QUANTS=ON \
  -DCMAKE_BUILD_TYPE=Release

cmake --build build -j$(nproc)

Recommended configurations

turbo4 (4.25 bpv) -- lossless quality, great compression

The safe default. Virtually no quality loss vs FP16 with ~3.8x KV cache compression and no speed penalty.

./build/bin/llama-server -m model.gguf -ngl 99 -fa \
  -ctk turbo4 -ctv turbo4

3-bit TCQ (3.25 bpv) -- best quality at 3-bit

Beats FP16 quality at short context, stays within 2% at long context. ~5x KV cache compression.

./build/bin/llama-server -m model.gguf -ngl 99 -fa \
  -ctk turbo3_tcq -ctv turbo3_tcq

2-bit TCQ (2.25 bpv) -- maximum compression

~7x KV cache compression. Best for fitting very long contexts in limited VRAM.

./build/bin/llama-server -m model.gguf -ngl 99 -fa \
  -ctk turbo2_tcq -ctv turbo2_tcq

Asymmetric 2.75 bpv -- best 2-bit quality

3-bit keys + 2-bit values. 15-17% lower KLD than the reverse, because adaptive alpha already compensates V quantization error.

./build/bin/llama-server -m model.gguf -ngl 99 -fa \
  -ctk turbo3_tcq -ctv turbo2_tcq

Scalar turbo3 / turbo2 (3.25 / 2.25 bpv) -- no trellis

Scalar quantization without TCQ. Faster encode, worse quality than TCQ equivalents.

# 3-bit scalar
./build/bin/llama-server -m model.gguf -ngl 99 -fa \
  -ctk turbo3 -ctv turbo3

# 2-bit scalar
./build/bin/llama-server -m model.gguf -ngl 99 -fa \
  -ctk turbo2 -ctv turbo2

Quality (KL-divergence, Qwen3.5-27B Q6_K, RTX 3090)

Lower is better. Measured against FP16 KV cache base logits.

Config bpv KLD @2K KLD @7K
turbo3_tcq (symmetric) 3.25 0.058 0.074
turbo3_tcq-K / turbo2_tcq-V 2.75 0.078 0.101
turbo2_tcq (symmetric) 2.25 0.101 0.136

3-bit TCQ at 2K context achieves lower perplexity than FP16 (5.802 vs 5.805) due to a mild regularizing effect from norm scaling.

Speed (Qwen3.5-27B Q6_K, RTX 3090)

Config Decode (tg64) vs q8_0
q8_0 31.04 tok/s --
turbo3_tcq 30.04 tok/s 97%
turbo3 (scalar) 30.04 tok/s 97%

Decode speed is constant across context lengths (30 tok/s at 4K, 65K, and 128K). Prefill uses tensor-core MMA path at 99%+ of q8_0 speed.

Custom codebooks

Trained codebooks are included in codebooks/. The defaults are compiled into the CUDA kernels, but you can override them:

TURBO_TCQ_CB=codebooks/3bit/product_aware_iter080.bin \
TURBO_TCQ_CB2=codebooks/2bit/product_aware_iter090.bin \
./build/bin/llama-server -m model.gguf -ngl 99 -fa \
  -ctk turbo3_tcq -ctv turbo3_tcq

Codebook training scripts are in scripts/tcq_train_*.py.

How it works

  1. FWHT rotation with random sign flips converts correlated KV vectors into i.i.d. Gaussian entries
  2. Viterbi encoding on a 512-state (3-bit) or 256-state (2-bit) right-shift trellis finds the globally optimal codeword assignment
  3. O(1) sliding-window decode -- each value decodes via a bit window lookup, no trellis traversal at inference
  4. Context-adaptive alpha -- logarithmic norm scaling formula automatically adjusts dequantization scale per context length

Supported models

Any GGUF model with head_dim that is a multiple of 128 works natively. Models with other head dimensions (e.g., Phi-3 at 96, Qwen3-0.6B at 64) are supported via automatic zero-padding.

Tested on: Qwen3.5-27B, Qwen3-32B, Gemma-3-27B, Gemma-4-31B, Harmonic-Hermes-9B, Phi-3-mini, and others.

Quick start

Getting started with llama.cpp is straightforward. Here are several ways to install it on your machine:

Once installed, you'll need a model to work with. Head to the Obtaining and quantizing models section to learn more.

Example command:

# Use a local model file
llama-cli -m my_model.gguf

# Or download and run a model directly from Hugging Face
llama-cli -hf ggml-org/gemma-3-1b-it-GGUF

# Launch OpenAI-compatible API server
llama-server -hf ggml-org/gemma-3-1b-it-GGUF

Description

The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.

  • Plain C/C++ implementation without any dependencies
  • Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
  • AVX, AVX2, AVX512 and AMX support for x86 architectures
  • RVV, ZVFH, ZFH, ZICBOP and ZIHINTPAUSE support for RISC-V architectures
  • 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory use
  • Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads GPUs via MUSA)
  • Vulkan and SYCL backend support
  • CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity

The llama.cpp project is the main playground for developing new features for the ggml library.

Models

Typically finetunes of the base models below are supported as well.

Instructions for adding support for new models: HOWTO-add-model.md

Text-only

Multimodal

Bindings
UIs

(to have a project listed here, it should clearly state that it depends on llama.cpp)

Tools
  • akx/ggify – download PyTorch models from Hugging Face Hub and convert them to GGML
  • akx/ollama-dl – download models from the Ollama library to be used directly with llama.cpp
  • crashr/gppm – launch llama.cpp instances utilizing NVIDIA Tesla P40 or P100 GPUs with reduced idle power consumption
  • gpustack/gguf-parser - review/check the GGUF file and estimate the memory usage
  • Styled Lines (proprietary licensed, async wrapper of inference part for game development in Unity3d with pre-built Mobile and Web platform wrappers and a model example)
  • unslothai/unsloth – 🦥 exports/saves fine-tuned and trained models to GGUF (Apache-2.0)
Infrastructure
  • Paddler - Open-source LLMOps platform for hosting and scaling AI in your own infrastructure
  • GPUStack - Manage GPU clusters for running LLMs
  • llama_cpp_canister - llama.cpp as a smart contract on the Internet Computer, using WebAssembly
  • llama-swap - transparent proxy that adds automatic model switching with llama-server
  • Kalavai - Crowdsource end to end LLM deployment at any scale
  • llmaz - ☸️ Easy, advanced inference platform for large language models on Kubernetes.
  • LLMKube - Kubernetes operator for llama.cpp with multi-GPU and Apple Silicon Metal support"
Games
  • Lucy's Labyrinth - A simple maze game where agents controlled by an AI model will try to trick you.

Supported backends

Backend Target devices
Metal Apple Silicon
BLAS All
BLIS All
SYCL Intel and Nvidia GPU
OpenVINO [In Progress] Intel CPUs, GPUs, and NPUs
MUSA Moore Threads GPU
CUDA Nvidia GPU
HIP AMD GPU
ZenDNN AMD CPU
Vulkan GPU
CANN Ascend NPU
OpenCL Adreno GPU
IBM zDNN IBM Z & LinuxONE
WebGPU [In Progress] All
RPC All
Hexagon [In Progress] Snapdragon
VirtGPU VirtGPU APIR

Obtaining and quantizing models

The Hugging Face platform hosts a number of LLMs compatible with llama.cpp:

You can either manually download the GGUF file or directly use any llama.cpp-compatible models from Hugging Face or other model hosting sites, by using this CLI argument: -hf <user>/<model>[:quant]. For example:

llama-cli -hf ggml-org/gemma-3-1b-it-GGUF

By default, the CLI would download from Hugging Face, you can switch to other options with the environment variable MODEL_ENDPOINT. The MODEL_ENDPOINT must point to a Hugging Face compatible API endpoint.

After downloading a model, use the CLI tools to run it locally - see below.

llama.cpp requires the model to be stored in the GGUF file format. Models in other data formats can be converted to GGUF using the convert_*.py Python scripts in this repo.

The Hugging Face platform provides a variety of online tools for converting, quantizing and hosting models with llama.cpp:

To learn more about model quantization, read this documentation

llama-cli

A CLI tool for accessing and experimenting with most of llama.cpp's functionality.

  • Run in conversation mode

    Models with a built-in chat template will automatically activate conversation mode. If this doesn't occur, you can manually enable it by adding -cnv and specifying a suitable chat template with --chat-template NAME

    llama-cli -m model.gguf

# > hi, who are you?
# Hi there! I'm your helpful assistant! I'm an AI-powered chatbot designed to assist and provide information to users like you. I'm here to help answer your questions, provide guidance, and offer support on a wide range of topics. I'm a friendly and knowledgeable AI, and I'm always happy to help with anything you need. What's on your mind, and how can I assist you today?
#
# > what is 1+1?
# Easy peasy! The answer to 1+1 is... 2!
  • Run in conversation mode with custom chat template 
    # use the "chatml" template (use -h to see the list of supported templates)
llama-cli -m model.gguf -cnv --chat-template chatml

# use a custom template
llama-cli -m model.gguf -cnv --in-prefix 'User: ' --reverse-prompt 'User:'
  • Constrain the output with a custom grammar 
    llama-cli -m model.gguf -n 256 --grammar-file grammars/json.gbnf -p 'Request: schedule a call at 8pm; Command:'

# {"appointmentTime": "8pm", "appointmentDetails": "schedule a a call"}

    The grammars/ folder contains a handful of sample grammars. To write your own, check out the GBNF Guide.

    For authoring more complex JSON grammars, check out https://grammar.intrinsiclabs.ai/

llama-server

A lightweight, OpenAI API compatible, HTTP server for serving LLMs.

  • Start a local HTTP server with default configuration on port 8080 
    llama-server -m model.gguf --port 8080

# Basic web UI can be accessed via browser: http://localhost:8080
# Chat completion endpoint: http://localhost:8080/v1/chat/completions
  • Support multiple-users and parallel decoding 
    # up to 4 concurrent requests, each with 4096 max context
llama-server -m model.gguf -c 16384 -np 4
  • Enable speculative decoding 
    # the draft.gguf model should be a small variant of the target model.gguf
llama-server -m model.gguf -md draft.gguf
  • Serve an embedding model 
    # use the /embedding endpoint
llama-server -m model.gguf --embedding --pooling cls -ub 8192
  • Serve a reranking model 
    # use the /reranking endpoint
llama-server -m model.gguf --reranking
  • Constrain all outputs with a grammar 
    # custom grammar
llama-server -m model.gguf --grammar-file grammar.gbnf

# JSON
llama-server -m model.gguf --grammar-file grammars/json.gbnf

llama-perplexity

A tool for measuring the perplexity 1 (and other quality metrics) of a model over a given text.

  • Measure the perplexity over a text file 
    llama-perplexity -m model.gguf -f file.txt

# [1]15.2701,[2]5.4007,[3]5.3073,[4]6.2965,[5]5.8940,[6]5.6096,[7]5.7942,[8]4.9297, ...
# Final estimate: PPL = 5.4007 +/- 0.67339
  • Measure KL divergence 
    # TODO

llama-bench

Benchmark the performance of the inference for various parameters.

  • Run default benchmark 
    llama-bench -m model.gguf

# Output:
# | model               |       size |     params | backend    | threads |          test |                  t/s |
# | ------------------- | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |
# | qwen2 1.5B Q4_0     | 885.97 MiB |     1.54 B | Metal,BLAS |      16 |         pp512 |      5765.41 ± 20.55 |
# | qwen2 1.5B Q4_0     | 885.97 MiB |     1.54 B | Metal,BLAS |      16 |         tg128 |        197.71 ± 0.81 |
#
# build: 3e0ba0e60 (4229)

llama-simple

A minimal example for implementing apps with llama.cpp. Useful for developers.

  • Basic text completion 
    llama-simple -m model.gguf

# Hello my name is Kaitlyn and I am a 16 year old girl. I am a junior in high school and I am currently taking a class called "The Art of

Contributing

  • Contributors can open PRs
  • Collaborators will be invited based on contributions
  • Maintainers can push to branches in the llama.cpp repo and merge PRs into the master branch
  • Any help with managing issues, PRs and projects is very appreciated!
  • See good first issues for tasks suitable for first contributions
  • Read the CONTRIBUTING.md for more information
  • Make sure to read this: Inference at the edge
  • A bit of backstory for those who are interested: Changelog podcast

Other documentation

Development documentation

Seminal papers and background on the models

If your issue is with model generation quality, then please at least scan the following links and papers to understand the limitations of LLaMA models. This is especially important when choosing an appropriate model size and appreciating both the significant and subtle differences between LLaMA models and ChatGPT:

XCFramework

The XCFramework is a precompiled version of the library for iOS, visionOS, tvOS, and macOS. It can be used in Swift projects without the need to compile the library from source. For example:

// swift-tools-version: 5.10
// The swift-tools-version declares the minimum version of Swift required to build this package.

import PackageDescription

let package = Package(
    name: "MyLlamaPackage",
    targets: [
        .executableTarget(
            name: "MyLlamaPackage",
            dependencies: [
                "LlamaFramework"
            ]),
        .binaryTarget(
            name: "LlamaFramework",
            url: "https://github.com/ggml-org/llama.cpp/releases/download/b5046/llama-b5046-xcframework.zip",
            checksum: "c19be78b5f00d8d29a25da41042cb7afa094cbf6280a225abe614b03b20029ab"
        )
    ]
)

The above example is using an intermediate build b5046 of the library. This can be modified to use a different version by changing the URL and checksum.

Completions

Command-line completion is available for some environments.

Bash Completion

$ build/bin/llama-cli --completion-bash > ~/.llama-completion.bash
$ source ~/.llama-completion.bash

Optionally this can be added to your .bashrc or .bash_profile to load it automatically. For example:

$ echo "source ~/.llama-completion.bash" >> ~/.bashrc

Dependencies

  • yhirose/cpp-httplib - Single-header HTTP server, used by llama-server - MIT license
  • stb-image - Single-header image format decoder, used by multimodal subsystem - Public domain
  • nlohmann/json - Single-header JSON library, used by various tools/examples - MIT License
  • miniaudio.h - Single-header audio format decoder, used by multimodal subsystem - Public domain
  • subprocess.h - Single-header process launching solution for C and C++ - Public domain

Footnotes

  1. https://huggingface.co/docs/transformers/perplexity ↩

About

LLM inference in C/C++

Resources

Readme

License

MIT license

Contributing

Contributing

Security policy

Security policy
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • C++ 52.2%
  • C 18.0%
  • Python 7.5%
  • Cuda 6.3%
  • HTML 3.4%
  • TypeScript 2.6%
  • Other 10.0%