Multimodal product matching system using LLaVA, BERT, and DINOv2 with Triton Inference, FAISS, and MongoDB
-
Updated
Sep 9, 2025 - Python
#
triton-inference
Here are 3 public repositories matching this topic...
High-performance Triton kernel library for LLM training with 12 fused operators (AttnRes, RMSNorm, RoPE, CrossEntropy, GRPO, JSD, FusedLinear, etc.) — up to 24x faster than PyTorch with 78% memory savings, outperforming Liger-Kernel on RTX 5090
-
Updated
Mar 21, 2026 - Python
Tungsten Alpha: A JAX-native, 7-layer Adelic-Riemannian Operating System. Implements resurgent gradient flow through discrete logic and Levi-Civita parallel transport for decentralized XLA clusters. Hardened for zero-jitter, systolic array execution.
high-performance-computing artificial-general-intelligence tpu jax riemannian-geometry riemannian-optimization fisher-information-matrix xla information-geometry jit-compilation natural-gradient parallel-transport machine-learning-infrastructure triton-inference orbax custom-jax-primitives hlo-fusion sensor-swarms manifold-learning-decentralized-ai
-
Updated
Mar 16, 2026 - Python
Improve this page
Add a description, image, and links to the triton-inference topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the triton-inference topic, visit your repo's landing page and select "manage topics."