openPangu
PulseAugur coverage of openPangu — every cluster mentioning openPangu across labs, papers, and developer communities, ranked by signal.
-
openPangu releases openPangu-2.0-Flash MoE model with 512k context
The openPangu-2.0-Flash model is a new Mixture-of-Experts (MoE) architecture boasting 92 billion total parameters and activating 6 billion parameters. It supports a context length of 512k tokens and was trained on 34 tr…
-
Huawei open-sources 92B-parameter openPangu-2.0-Flash model
Huawei has officially open-sourced its openPangu-2.0-Flash model, which features 92 billion parameters. The company announced that related components of the openPangu-2.0 model will be progressively open-sourced startin…
-
OpenPangu LLM quantization on Ascend NPUs shows 8-bit is lossless, 4-bit degrades 1B model
A new study investigates the effectiveness of various post-training quantization methods for the OpenPangu large language models when deployed on Ascend NPUs. Researchers found that 8-bit weight-only quantization is nea…