conftrace_

llama2 70b

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

block design (1) gpus (1) binarization (1) 1-bit weights (1) perplexity (1) tensor parallelism (1) communication overhead (1) synchronization (1) post-training quantization (1) quantization (1)

Papers

SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models ICML 2025 BiLLM: Pushing the Limit of Post-Training Quantization for LLMs ICML 2024