Submitted by SpiridonSunRotator 25 Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization IST Austria Distributed Algorithms and Systems Lab 3
Submitted by softmax 40 The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm IST Austria Distributed Algorithms and Systems Lab 3
Submitted by BlackSamorez 77 Quartet: Native FP4 Training Can Be Optimal for Large Language Models IST Austria Distributed Algorithms and Systems Lab 102 2
Submitted by d-alistarh 43 QuEST: Stable Training of LLMs with 1-Bit Weights and Activations IST Austria Distributed Algorithms and Systems Lab 74 3
1 MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models IST Austria Distributed Algorithms and Systems Lab 913