Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
1.Huawei releases MACaQ, its internal quantizer for local inference (github.com/huawei-csl)
132 points by thefox96 1 day ago | past | 31 comments
2.KVarN: Native vLLM backend for KV-cache quantization by Huawei (github.com/huawei-csl)
143 points by theanonymousone 5 months ago | past | 16 comments
3.Sinkhorn: Make LLMs even smaller through quantisation while maintaining accuracy (github.com/huawei-csl)
4 points by ilitirit on Oct 4, 2025 | past | 1 comment

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: