RetroSearch Browse

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/mukel/llama3.java below:

mukel/llama3.java: Practical Llama 3 inference in Java

Practical Llama 3, 3.1 and 3.2 inference implemented in a single Java file.

This project is the successor of llama2.java based on llama2.c by Andrej Karpathy and his excellent educational videos.

Besides the educational value, this project will be used to test and tune compiler optimizations and features on the JVM, particularly for the Graal compiler.

Single file, no dependencies
GGUF format parser
Llama 3 tokenizer based on minbpe
Llama 3 inference with Grouped-Query Attention
Support Llama 3.1 (ad-hoc RoPE scaling) and 3.2 (tie word embeddings)
Support F16, BF16 weights + Q8_0 and Q4_0 quantizations
Fast matrix-vector multiplication routines using Java's Vector API
Simple CLI with --chat and --instruct modes.
GraalVM's Native Image support (EA builds here)
AOT model pre-loading for instant time-to-first-token

Interactive --chat mode in action:

Presented at Devoxx Belgium, 2024

Download pure Q4_0 and (optionally) Q8_0 quantized .gguf files from:

The pure Q4_0 quantized models are recommended, except for the very small models (1B), please be gentle with huggingface.co servers:

# Llama 3.2 (3B)
curl -L -O https://huggingface.co/mukel/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_0.gguf

# Llama 3.2 (1B)
curl -L -O https://huggingface.co/mukel/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q8_0.gguf

# Llama 3.1 (8B)
curl -L -O https://huggingface.co/mukel/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_0.gguf

# Llama 3 (8B)
curl -L -O https://huggingface.co/mukel/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-Q4_0.gguf

# Optionally download the Q8_0 quantized models
# curl -L -O https://huggingface.co/mukel/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-Q8_0.gguf
# curl -L -O https://huggingface.co/mukel/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q8_0.gguf

Optional: quantize to pure Q4_0 manually

In the wild, Q8_0 quantizations are fine, but Q4_0 quantizations are rarely pure e.g. the token_embd.weights/output.weights tensor are quantized with Q6_K, instead of Q4_0.
A pure Q4_0 quantization can be generated from a high precision (F32, F16, BFLOAT16) .gguf source with the llama-quantize utility from llama.cpp as follows:

./llama-quantize --pure ./Meta-Llama-3-8B-Instruct-F32.gguf ./Meta-Llama-3-8B-Instruct-Q4_0.gguf Q4_0

Java 21+ is required, in particular the MemorySegment mmap-ing feature.

jbang is a perfect fit for this use case, just:

Or execute directly, also via jbang:

chmod +x Llama3.java
./Llama3.java --help

java --enable-preview --source 21 --add-modules jdk.incubator.vector Llama3.java -i --model Meta-Llama-3-8B-Instruct-Q4_0.gguf

Optional: Makefile + manually build and run

A simple Makefile is provided, run make to produce llama3.jar or manually:

javac -g --enable-preview -source 21 --add-modules jdk.incubator.vector -d target/classes Llama3.java
jar -cvfe llama3.jar com.llama4j.Llama3 LICENSE -C target/classes .

Run the resulting llama3.jar as follows:

java --enable-preview --add-modules jdk.incubator.vector -jar llama3.jar --help

Compile to native via make (recommended):

Or directly:

native-image -H:+UnlockExperimentalVMOptions -H:+VectorAPISupport -H:+ForeignAPISupport -O3 -march=native --enable-preview --add-modules jdk.incubator.vector --initialize-at-build-time=com.llama4j.FloatTensor -Djdk.incubator.vector.VECTOR_ACCESS_OOB_CHECK=0 -jar llama3.jar -o llama3

Run as Native Image:

./llama3 --model Llama-3.2-1B-Instruct-Q8_0 --chat

Llama3.java supports AOT model preloading, enabling 0-overhead, instant inference, with minimal TTFT (time-to-first-token).

To AOT pre-load a GGUF model:

PRELOAD_GGUF=/path/to/model.gguf make native

A specialized, larger binary will be generated, with no parsing overhead for that particular model. It can still run other models, although incurring the usual parsing overhead.

GraalVM now supports more Vector API operations. To give it a try, you need GraalVM for JDK 24 – get the EA builds from oracle-graalvm-ea-builds or sdkman: sdk install java 24.ea.20-graal.
By default, the "preferred" vector size is used, it can be force-set with -Dllama.VectorBitSize=0|128|256|512, 0 means disabled.

Vanilla llama.cpp built with make.

./llama-cli --version                                                                                                                                                                          130 ↵
version: 3862 (3f1ae2e3)
built with cc (GCC) 14.2.1 20240805 for x86_64-pc-linux-gnu

Executed as follows:

./llama-bench -m Llama-3.2-1B-Instruct-Q4_0.gguf -p 0 -n 128

taskset -c 0-15 ./llama3 \
  --model ./Llama-3-1B-Instruct-Q4_0.gguf \
  --max-tokens 128 \
  --seed 42 \
  --stream false \
  --prompt "Why is the sky blue?"

Hardware specs: 2019 AMD Ryzen 3950X 16C/32T 64GB (3800) Linux 6.6.47.

**Notes
Running on a single CCD e.g. taskset -c 0-15 ./llama3 ... since inference is constrained by memory bandwidth.

MIT

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4