Видео ютуба по тегу Weight Quantization

Sinq: нормализованное по Синкхорну квантование для низкоточных весов LLM без калибровки
Sinq: нормализованное по Синкхорну квантование для низкоточных весов LLM без калибровки
DATE '25 - Column-wise Quantization of Weights and Partial Sums... (presented by: Jiyoon Kim)
DATE '25 - Column-wise Quantization of Weights and Partial Sums... (presented by: Jiyoon Kim)
CognitionTO Papers - The Super Weight in Large Language Models
CognitionTO Papers - The Super Weight in Large Language Models
Faster-Grad-CAM(Weight Quantization) + Tensorflow Lite + Corei7 + 4 Threads
Faster-Grad-CAM(Weight Quantization) + Tensorflow Lite + Corei7 + 4 Threads
692: Lossless LLM Weight Compression: Run Huge Models on a Single GPU — with Jon Krohn
692: Lossless LLM Weight Compression: Run Huge Models on a Single GPU — with Jon Krohn
Tiny Yolo v3 on the
Tiny Yolo v3 on the "pedestrian" sequence with Pyramid Vector Quantized weights
EfficientML.ai Lecture 6 - Quantization (Part II) (MIT 6.5940, Fall 2023)
EfficientML.ai Lecture 6 - Quantization (Part II) (MIT 6.5940, Fall 2023)
MICROSOFT'S WINA: WEIGHT INFORMED NEURON ACTIVATION FOR ACCELERATING LARGE LANGUAGE MODEL INFERENCE
MICROSOFT'S WINA: WEIGHT INFORMED NEURON ACTIVATION FOR ACCELERATING LARGE LANGUAGE MODEL INFERENCE
CNN Weight Compressing using Vector Quantization
CNN Weight Compressing using Vector Quantization
TinyML Book Screencast #4 - Quantization
TinyML Book Screencast #4 - Quantization
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Quantization in vLLM: From Zero to Hero
Quantization in vLLM: From Zero to Hero
APEC 6/11, Part #3 – Jim Buckeyne – Quantized Weight
APEC 6/11, Part #3 – Jim Buckeyne – Quantized Weight
ChatGPT in your pocket? Quantization in LLMs
ChatGPT in your pocket? Quantization in LLMs
SINQ: Calibration-Free Low-Bit LLM Quantization
SINQ: Calibration-Free Low-Bit LLM Quantization
Guest Lecture by Tianyi Zhang: Faster & Cheaper LLMs with Weight and Key-value Cache Quantization
Guest Lecture by Tianyi Zhang: Faster & Cheaper LLMs with Weight and Key-value Cache Quantization
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
EE545 (Week 6) More on Quantization and Quantization Aware Training (Part II)
EE545 (Week 6) More on Quantization and Quantization Aware Training (Part II)
Neural network quantization with AdaRound
Neural network quantization with AdaRound
[2023 Best AI Paper] SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressio
[2023 Best AI Paper] SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressio
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
1bit llm#largelanguagemodels#quantization#generativeai#weight#precision#training#gpu#memory#ai#maths
1bit llm#largelanguagemodels#quantization#generativeai#weight#precision#training#gpu#memory#ai#maths
FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs
FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs
Accumulator-Aware Quantization
Accumulator-Aware Quantization
GPTQModel - Easy LLM Quantization and Inference Toolkit
GPTQModel - Easy LLM Quantization and Inference Toolkit