beehive-lab/GPULlama3.java

View on GitHub

GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

Stars: 274
Forks: 37
Open beginner issues: 0
Indexed issues: 18
Avg merge: 5d 1h
Merged PRs (30d): 2

Dominant language: Java
License: MIT
Last GitHub push: Sep 11, 2026
Latest indexed: Sep 14, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue

Open All

18 issues indexed so far

Add Junit5 and a set of initial tests Open

good first issue

beehive-lab/GPULlama3.java#14 · 3 comments · 0 reactions · 2 assignees · Indexed Sep 14, 2026
Add Basic Error Handling for Missing Model Files Open

good first issue

beehive-lab/GPULlama3.java#15 · 4 comments · 0 reactions · 1 assignee · Indexed Sep 14, 2026
Set Up Linters and Code Style Checkers Open

good first issue

beehive-lab/GPULlama3.java#16 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Support for Gemma Models Open

enhancement models

beehive-lab/GPULlama3.java#20 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 14, 2026
Build GUI Chatbox for GPULlama3.java Inference with embedded GPU resource monitoring Open

good first issue Tooling

beehive-lab/GPULlama3.java#24 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Add pre-commit hook Open

good first issue Tooling

beehive-lab/GPULlama3.java#29 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
OutOfMemory / Misleading Hint Open

documentation enhancement

beehive-lab/GPULlama3.java#30 · 1 comment · 1 reaction · 1 assignee · Indexed Sep 14, 2026
Improve error handling on out of memory exception to provide relevant solution for the llama Open

documentation enhancement

beehive-lab/GPULlama3.java#31 · 1 comment · 0 reactions · 4 assignees · Indexed Sep 14, 2026
support for llama3.2 vision Open

question

beehive-lab/GPULlama3.java#43 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 14, 2026
TornadoTaskRuntimeException when using Phi-3-mini-4k-instruct-fp16.gguf during TornadoVM initialization Open

bug

beehive-lab/GPULlama3.java#72 · 5 comments · 0 reactions · 1 assignee · Indexed Sep 14, 2026
Wrong download link for Qwen3 (1.7B) - FP16, Qwen3 (4B) - FP16 and Qwen3 (8B) - FP16 Open

beehive-lab/GPULlama3.java#76 · 0 comments · 1 reaction · 1 assignee · Indexed Sep 14, 2026
[POC] Minimal Kernel Autotuning Support Open

enhancement

beehive-lab/GPULlama3.java#96 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 14, 2026
Use withCudaGraphs on PTX backend Open

beehive-lab/GPULlama3.java#100 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 14, 2026
Support direct execution of K-quant GGUF weights on GPU (Q4_K, Q5_K, Q6_K) Open

enhancement quantization

beehive-lab/GPULlama3.java#118 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Add .claude dir with relevant skills Open

enhancement

beehive-lab/GPULlama3.java#119 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Roadmap: vLLM-style serving features for TornadoVM batched decode Open

beehive-lab/GPULlama3.java#130 · 1 comment · 0 reactions · 4 assignees · Indexed Sep 14, 2026
Reduce external implementation types exposed by the GPULlama3 integration API Open

1.0.1 good first issue refactoring

beehive-lab/GPULlama3.java#141 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 14, 2026
Support the Qwen3.5 architecture Open

beehive-lab/GPULlama3.java#143 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 14, 2026

beehive-lab/GPULlama3.java

Get new issues in your inbox