Sublime
An inspiration engine for ideas
Wake up babe new SOTA quantization method just dropped!!!!
TEQ (Trainable Equivalent Transformation) preserves FP32 precision of the model output while using low-precision quantization. Training requires only 1K steps and < 1% of the original model’s trainable parameters.
Results are on par... See more
Harper Carrollx.comdeep-tech
Juan Orbea and • 33 cards
Quantum
Ashmini Perera • 1 card
Linear scaling achieved with multiple DeepSeek v3.1 instances. 4x macs = 4x throughput.
2x M3 Ultra Mac Studios = 1x DeepSeek @ 14 tok/sec
4x M3 Ultra Mac Studios = 2x DeepSeek @ 28 tok/sec
DeepSeek V3.1 is a 671B parameter model - so at its native 8-bit... See more
Matt Betonx.comeXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization
https://t.co/NyV4BNPfBO
arXiv Dailyx.comUsing light as a neural network, as this viral video depicts, is actually closer than you think. In 5-10yrs, we could have matrix multiplications in constant time O(1) with 95% less energy. This is the next era of Moore's Law.
Let's talk about Silicon Photonics...
1/9 https://t.co/vn9K47xDvU
Deedyx.com
