Article
SDXL in 4 steps with Latent Consistency LoRAs
- +5
•
15
Tek Raj Awasthi
Tekraj15
AI & ML interests
Advanced Deep Learning |
Multimodal Gen AI(LLM/VLM Compression, Fine-tuning, Post-training, RAG, Agents) |
High Performance/Edge Computation; GPU sounds sexy, but "Edge Optimization" gives me real orgasm!
Recent Activity
liked
a Space
5 days ago
r3gm/wan2-2-fp8da-aoti-preview
upvoted
an
article
6 days ago
SDXL in 4 steps with Latent Consistency LoRAs
liked
a Space
8 days ago
Tekraj15/Sketch-to-Render-AI
Organizations
upvoted
an
article
6 days ago
upvoted
a
paper
29 days ago
upvoted
a
paper
30 days ago
upvoted
2
articles
6 months ago
Article
From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels
•
91
Article
Code a simple RAG from scratch
•
293