#python#large_language_models#machine_learning_systems#natural_language_processing
Flash Linear Attention (FLA) is a fast, memory-efficient library for advanced linear attention models used in transformers, written in PyTorch and Triton, and compatible with NVIDIA, AMD, and Intel GPUs. It offers many state-of-the-art linear attention models and fused modules that speed up training and reduce memory use. You can easily replace standard attention layers in your models with FLA’s efficient versions, improving training and inference speed, especially for long sequences. FLA supports hybrid models mixing linear and standard attention, and integrates with Hugging Face Transformers for easy use and evaluation. This helps you train and run large language models faster and with less memory, making your AI projects more efficient and scalable.
https://github.com/fla-org/flash-linear-attention
Choc Chip Banana Bread ✨🍌🤎
Ingredients:
* 3 large ripe bananas (360–380 g)
* 130 g unsalted butter (will reduce to \~115 g once browned)
* 180 g dark brown sugar (+ 1–2 tbsp for topping)
* 2 large eggs
* 250 g plain flour
* 1 tsp baking soda
* ½ tsp salt
* ½ tsp cinnamon
* 70–100 g dark chocolate, chopped
* Optional: chopped nuts
#dinner
@dishes
My Kind of Girl Dinner 😮💨🍚🥒
Ingredients:
For the salmon:
* 2 salmon fillets (skin removed, cut into cubes)
* 2 tbsp soy sauce
* 1 tbsp oyster sauce
* 1 tsp brown sugar
* 2 tsp minced garlic
* 1 tbsp sriracha
* ¼ tsp chili flakes
For the rice & toppings:
* 100 g sushi rice (cooked)
* 1 tsp apple cider vinegar
* ½ tsp salt
* ½ tsp sugar
* Pinch of chili flakes
* ¼ cucumber, thinly sliced
* ¼ small onion, thinly sliced
* Handful of edamame (cooked)
* Black & white sesame seeds, for topping
#dinner
@dishes