-
05:06
(UTC -12:00) - @mohdanish06
Pinned Loading
-
AeroMail-Intelligence
AeroMail-Intelligence PublicAn end-to-end, production-ready Retrieval-Augmented Generation (RAG) system built with Python, FastAPI, PostgreSQL, Qdrant, MLflow, and a locally hosted open-source LLM. The project includes docume…
Python 1
-
flash_attn_forward_kernel
flash_attn_forward_kernel PublicFlashInfer is an experimental GPU kernel-engineering project focused on implementing, validating, and optimizing FlashAttention-style computation from first principles.
Python
-
ForgeServe
ForgeServe PublicForgeServe is a small, modular LLM inference engine built with Python, PyTorch, and Hugging Face Transformers, designed to make modern inference systems understandable by implementing them step-by-…
Python
-
LatentForge
LatentForge PublicA PyTorch workbench for building and exploring transformer architectures from first principles.
Python 1
If the problem persists, check the GitHub status page or contact support.


