- San Francisco, CA
-
10:00
(UTC -08:00) - https://orcid.org/0009-0004-2868-6689
- @sozercan
- @[email protected]
- in/sozercan
- @sozercan.bsky.social
Highlights
- All languages
- AppleScript
- AutoIt
- Batchfile
- Bicep
- C
- C#
- C++
- CSS
- Crystal
- Cuda
- Dart
- Dockerfile
- Go
- HCL
- HLSL
- HTML
- Haskell
- Java
- JavaScript
- Jsonnet
- Jupyter Notebook
- Kotlin
- Lua
- MDX
- Makefile
- Markdown
- OCaml
- Objective-C
- Objective-C++
- Open Policy Agent
- PHP
- Perl
- PowerShell
- Python
- RPM Spec
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Smarty
- Starlark
- Svelte
- Swift
- TypeScript
- Vue
- YARA
- Zig
Starred repositories
LLM Instance gateway implementation.
Retry a command with exponential backoff and jitter (+ Starlark expressions)
Launch configurable virtual machines with libkrun
A dynamic library providing Virtualization-based process isolation capabilities
Kubernetes Native Container Build Service
Kube Startup CPU Boost is a controller that increases CPU resource requests and limits during Kubernetes workload startup time
Gorgonia is a library that helps facilitate machine learning in Go.
Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
A simple screen parsing tool towards pure vision based GUI agent
Packages for a K8 API Server object information pipeline
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
A GitHub App that acts like a Security Token Service (STS) for the Github API
An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.
Setup and configure nodes to support GPUs on k8s, with a focus on AKS nodes. This repo contains steps to build a container image with the Nvidia driver, and dependencies for integration.