conftrace_

1-bit weights

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hadamard normalization (1) mse-optimal fitting (1) trust gradient estimator (1) binarization (1) activation (1) llama2 70b (1) perplexity (1) quantization-aware training (1) post-training quantization (1) quantization (1)

Papers

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations ICML 2025 BiLLM: Pushing the Limit of Post-Training Quantization for LLMs ICML 2024