Pinned Repositories
b63
Micro-benchmarking library for C and C++ with PMU counters tracking
cubestat
Horizon chart for CPU/GPU/Neural Engine utilization monitoring on Apple M1/M2 and nVidia GPUs on Linux
experiments
fewlines
Create histograms, time series charts and dashboards in command-line output and log files.
flamereport
FlameGraph visualization for terminal
hcl
Horizon chart tool for terminal.
llama_duo
asynchronous/distributed speculative evaluation for llama3
qna
AI pretends to be paper/textbook author, you can ask it questions about the paper as a whole, specific parts of it right in the PDF viewing app (e.g. Apple Preview) using annotations and see the replies there.
rlscout
In progress attempt to use Deep RL to solve some game
slowllama
Finetune llama2-70b and codellama on MacBook Air without quantization
okuvshynov's Repositories
okuvshynov/slowllama
Finetune llama2-70b and codellama on MacBook Air without quantization
okuvshynov/b63
Micro-benchmarking library for C and C++ with PMU counters tracking
okuvshynov/llama_duo
asynchronous/distributed speculative evaluation for llama3
okuvshynov/cubestat
Horizon chart for CPU/GPU/Neural Engine utilization monitoring on Apple M1/M2 and nVidia GPUs on Linux
okuvshynov/flamereport
FlameGraph visualization for terminal
okuvshynov/fewlines
Create histograms, time series charts and dashboards in command-line output and log files.
okuvshynov/qna
AI pretends to be paper/textbook author, you can ask it questions about the paper as a whole, specific parts of it right in the PDF viewing app (e.g. Apple Preview) using annotations and see the replies there.
okuvshynov/hcl
Horizon chart tool for terminal.
okuvshynov/experiments
okuvshynov/rlscout
In progress attempt to use Deep RL to solve some game
okuvshynov/scrambled
okuvshynov/sloth
okuvshynov/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
okuvshynov/okuvshynov.github.io
okuvshynov/rwp
okuvshynov/vimrc
okuvshynov/llama.cpp
LLM inference in C/C++