Hacker Newsnew | past | comments | ask | show | jobs | submit | mikepapadim's commentslogin

Twice a day, Claude Cowork searched SpareRoom, OpenRent, Rightmove and Zoopla, filtered out student flats and 3+ bed houses, wrote personalised outreach messages forevery good listing, and emailed me a digest I could act on from my phone.

As a result, I managed to put down a deposit for a decent 1 bed flat in London in just under a week for the price people asking for a room!

Totally skipped all the manual searching of new ads etc.

I create a repo so others can take ideas or even reuse it.

Just adapt your preferences

Just with Claude cowork + Claude in Chrome + Gmail MCP


- [Llama3.java] https://github.com/mukel/llama3.java - [Gemma4.java] https://github.com/mukel/gemma4.java - [Jlama] https://github.com/tjake/Jlama - [GPULlama3.java https://github.com/beehive-lab/GPULlama3.java - [Qxotic] https://github.com/qxoticai/qxotic - [TornadoVM]https://github.com/beehive-lab/TornadoVM


- [Llama3.java](https://github.com/mukel/llama3.java) - [Gemma4.java](https://github.com/mukel/gemma4.java) - [Jlama](https://github.com/tjake/Jlama) - [GPULlama3.java](https://github.com/beehive-lab/GPULlama3.java) - [Qxotic](https://github.com/qxoticai/qxotic) - [TornadoVM](https://github.com/beehive-lab/TornadoVM)


I'm exploring an idea to reduce GPU dispatch overhead in a Java-based runtime, TornadoVM, which executes compute operations from TornadoVM bytecodes.


Yes, when you use the PTX backend it supports Tensor Cores.It has also implementation for flash attention. You can also write your own kernels, have a look here: https://github.com/beehive-lab/GPULlama3.java/blob/main/src/... https://github.com/beehive-lab/GPULlama3.java/blob/main/src/...


TornadoVM GitHub has no mentions of tensor cores or WMMA instructions. The only mention of tensor cores is in 2024 and states they are not used: https://github.com/beehive-lab/TornadoVM/discussions/393


https://github.com/beehive-lab/TornadoVM/pull/732 https://github.com/beehive-lab/TornadoVM/pull/313


I believe these are SIMD. Tensor cores require MMA family of instructions. Ask me how I know. :)

https://github.com/m4rs-mt/ILGPU/compare/master...lostmsu:IL...

Good article: https://alexarmbr.github.io/2024/08/10/How-To-Write-A-Fast-M...


https://github.com/beehive-lab/GPULlama3.java


Highlights Simpler execution via Java argfiles Improved performance on FP16/Int8 LLM Inference on hashtag#Nvidia GPUs Extended reduced precision type support for GPUs (Int8, fp16) Zero-copy object support through project Panama Support for compressed oops on modern JVMs New cross-platform SDK distribution (soon hashtag#SDKMAN! https://lnkd.in/d8pGHYy5) Official TornadoVM dependencies now published on Maven Central. (https://lnkd.in/dDRZj8ru)


https://github.com/beehive-lab/TornadoVM


  Location: UK
  Remote: Yes
  Willing to relocate: No
  Technologies: Java, C++, Python, Cuda, OpenCL, Docker, ONNXRT,Git, Apache TVM, Compilers, GPUs
  Résumé/CV:https://github.com/mikepapadim && https://www.linkedin.com/in/michalis-papadimitriou/
  Email:mpapadimitriou92 [ΑΤ] gmail.com


https://github.com/beehive-lab/GPULlama3.java

We took Llama3.java and we ported TornadoVM to enable GPU code generation. Apparrently, the first beta version runs on Nnvidia GPUs, while getting a bit more than 100 toks/sec for 3B model on FP16.

All the inference code offloaded to the GPU is in pure-Java just by using the TornadoVM apis to express the computation.

Runs Llama3 and Mistral models in GGUF format.

It is fully open-sourced, so give it a try. It currently run on Nvidia GPUs (OpenCL & PTX), Apple Silicon GPUs (OpenCL), and Intel GPUs and Integrated Graphics (OpenCL).


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: