Note to the reviewers/shipwright/fraud squad
so i accidentally added my home folder to the hackatime project and and when i contacted the fraud squad they told me to write a note so can you please deduct around 10 hours please also i attached a demo video of the benchmark script running for the ppl that dont want to download models and set my project up

removed multimodal and fixed the performance issue

so im writing this devlog the second time because stardance logged me out when i tried to post it and it didnt save it sadly so i have to write it again i guess but as the title said i removed the multimodal code basically because it was a pain to maintain and it broke with every update so i just wanted to focus on just closely matching llama.cpp on text speed as a solo developer project and i think i kinda achieved that because in the generation speed its only a few tokens of difference so i think the project is basically finished now and i maybe add a few small changes to it or ship it now but i dont know yet but i hope that someone will like my project even if it was a bit more boring then my other projects

Fixed some bugs and improved the performance in my free time

so i had some time on the weekend and the days i didnt go to school to fix

• added a benchmark shell script to compare the performance against ollama and llama.cpp for testing and for generating performance graphs
• now the vision tensors are run on the gpu too so the model wont get bottle necked by my laptops pci express bus speeds and uses the gpus memory instead
  so this or maybe another one will be probably the last devlog for this project because it has been super hard to develop this and kinda a pain to maintain and try to get it to the performance levels of modern interference libraries and i dont have much free time anymore because of school maybe i will continue development but idk

Fixed some bugs and improved the performance in my free time

so i had some time on the weekend and the days i didnt go to school to fix

• added a benchmark shell script to compare the performance against ollama and llama.cpp for testing and for generating performance graphs
• now the vision tensors are run on the gpu too so the model wont get bottle necked by my laptops pci express bus speeds and uses the gpus memory instead
  so this or maybe another one will be probably the last devlog for this project because it has been super hard to develop this and kinda a pain to maintain and try to get it to the performance levels of modern interference libraries and i dont have much free time anymore because of school maybe i will continue development but idk

Working cuda and ci pipeline but sadly i cant work on this project anymore because school started

So working on this project required quite a beefy and heavy computer and i dont want to carry one so sadly i dont have time to continue on this project in this time so after adding a working cuda gpu backend and a ci pipeline so ppl dont have to compile it from the source code and have nvcc to even try i think this is the end of this project for the current time being and i hope that someone will find this
So this is what i added:

• added a cuda backend with a fatbin kernel so it will work on multiple compute levels
• a github actions ci pipeline to generate verified releases for the ppl who dont want to compile everything for themselves

Working cuda and ci pipeline but sadly i cant work on this project anymore because school started

So working on this project required quite a beefy and heavy computer and i dont want to carry one so sadly i dont have time to continue on this project in this time so after adding a working cuda gpu backend and a ci pipeline so ppl dont have to compile it from the source code and have nvcc to even try i think this is the end of this project for the current time being and i hope that someone will find this
So this is what i added:

• added a cuda backend with a fatbin kernel so it will work on multiple compute levels
• a github actions ci pipeline to generate verified releases for the ppl who dont want to compile everything for themselves

Devlog 2: Finally working multimodal audio and video support

So after a lot of trial and error i finally added multimodal audio and video support because they were the only two things missing from a complete cpu engine because i wanted a fully working cpu reference before doing anything with cuda and stuff but i want to get cuda working asap because the smaller models that i have been testing that would run on my cpu with a good speed they kinda have bad multimodal performance
Thank you for reading my devlog

Devlog 2: Finally working multimodal audio and video support

So after a lot of trial and error i finally added multimodal audio and video support because they were the only two things missing from a complete cpu engine because i wanted a fully working cpu reference before doing anything with cuda and stuff but i want to get cuda working asap because the smaller models that i have been testing that would run on my cpu with a good speed they kinda have bad multimodal performance
Thank you for reading my devlog

First devlog for this new project

So i decided to start this new project while waiting for my other project getting reviewed

Why did i do this:

I was kinda bored waiting for my other project to be reviewed by ppl and i wanted to try out zig so i thought this is a great toy project idea to play with in zig

What models are tested (others might work but i havent tested them):

• smollm2-360m
• gemma 4 and its variants with curently only image multimodal working but sound and video might be added in the future

Thank you for reading my devlog

First devlog for this new project

So i decided to start this new project while waiting for my other project getting reviewed

Why did i do this:

I was kinda bored waiting for my other project to be reviewed by ppl and i wanted to try out zig so i thought this is a great toy project idea to play with in zig

What models are tested (others might work but i havent tested them):

• smollm2-360m
• gemma 4 and its variants with curently only image multimodal working but sound and video might be added in the future

Thank you for reading my devlog

Devlog 11: Fixing a few bugs and getting the app ready to ship

So in this time i havent done a lot of like cool stuff rather i was fixing a few bugs that broke the messaging feature and image attachment loading because i wanted to showcase those in my demo video and i fixed the github action so ppl can download an apk for the latest version if they want to try it out on their own legacy device also sorry for not writing a dev log sooner i was kinda busy but now i finally got the time to get the project into a ready to ship state

Devlog 11: Fixing a few bugs and getting the app ready to ship

So in this time i havent done a lot of like cool stuff rather i was fixing a few bugs that broke the messaging feature and image attachment loading because i wanted to showcase those in my demo video and i fixed the github action so ppl can download an apk for the latest version if they want to try it out on their own legacy device also sorry for not writing a dev log sooner i was kinda busy but now i finally got the time to get the project into a ready to ship state

Devlog 10: Finally added image sending/receiving support

So the next thing i taught i would add to my app is image sending and receiving support because that is like kinda a basic feature that any messaging app needs so i added

• image reviving
• sending images from the phones storage and via taking a picture with the camera

adding these was kinda annoying with figuring out all the correct endpoints and stuff but i think it was worth it in the end

Devlog 10: Finally added image sending/receiving support

So the next thing i taught i would add to my app is image sending and receiving support because that is like kinda a basic feature that any messaging app needs so i added

• image reviving
• sending images from the phones storage and via taking a picture with the camera

adding these was kinda annoying with figuring out all the correct endpoints and stuff but i think it was worth it in the end

Devlog 9: New features and a bit of an ui overhaul

So I decided to make the ui a bit more pretty and a few new features
So this is what i added:

• a new cleaner ui
• contact profile picture support
• message time stamping in the ui
• dark theme and theme switcher with persistence

these are just like qol improvements that i decided to add into the app nothing special but like i missed a few features like the dark theme myself so nothing major but i hope these changes makes the app more usable to ppl

Devlog 9: New features and a bit of an ui overhaul

So I decided to make the ui a bit more pretty and a few new features
So this is what i added:

• a new cleaner ui
• contact profile picture support
• message time stamping in the ui
• dark theme and theme switcher with persistence

these are just like qol improvements that i decided to add into the app nothing special but like i missed a few features like the dark theme myself so nothing major but i hope these changes makes the app more usable to ppl

Devlog 8 Working name syncing

So after a lot of work i finally made it work so it can show the name that you entered on the signal set up or the devices not just the phone numbers or just unknown sender or just the user id on my app so i guess another feature added now but i still want to add a few stuff before shipping

Devlog 8 Working name syncing

So after a lot of work i finally made it work so it can show the name that you entered on the signal set up or the devices not just the phone numbers or just unknown sender or just the user id on my app so i guess another feature added now but i still want to add a few stuff before shipping