Skip to content

Pull requests: beehive-lab/GPULlama3.java

New pull request New
10 Open 46 Closed
10 Open 46 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[WIP] Manipulation of Q8_0 tensors with Tornado ByteArrays
#79 opened Dec 4, 2025 by orionpapadakis • Draft
[FP16] Improved performance by fusing dequantize with compute in kernels: 20-30% Inference Speedup
#78 opened Dec 3, 2025 by mikepapadim Loading…
@mikepapadim
RMS normalization kernel optimization by fusing the reduction kernel and context mapping kernel
#77 opened Dec 1, 2025 by yrq0208 Loading…
5
[Docs] Refine documentation and README.md
#75 opened Nov 27, 2025 by mikepapadim Loading…
15
Copy-in embeddings in reduced precision and handle precision conversion during inference
#73 opened Nov 26, 2025 by mikepapadim Loading…
@mikepapadim
24
Add INTEGRATIONS.md showcasing LangChain4j and Quarkus integration ex…
#68 opened Nov 14, 2025 by mikepapadim Loading…
1
Add Q4_0 quantization support for all models in TornadoVM path
#67 opened Nov 13, 2025 by mikepapadim • Draft
26
[WIP][models] Add support for Google's Gemma3 models
#61 opened Nov 2, 2025 by mikepapadim Loading…
35
Rest API support
#49 opened Sep 8, 2025 by mikepapadim Loading…
@mikepapadim
12
Add GUI Chatbox for GPULlama3.java Inference Tooling
#33 opened Jun 25, 2025 by svntax Loading…
@svntax
13
ProTip! no:milestone will show everything without a milestone.