From 2473659e76ec0b15af16c141b712e151b3bab441 Mon Sep 17 00:00:00 2001 From: egvenediktov Date: Sun, 10 May 2026 23:49:21 +0300 Subject: [PATCH] [NPU]Documentation update for communications quantization feature (#24668) --- docs_new/docs/advanced_features/server_arguments.mdx | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/docs_new/docs/advanced_features/server_arguments.mdx b/docs_new/docs/advanced_features/server_arguments.mdx index f44b423ef..7a16ce1d8 100644 --- a/docs_new/docs/advanced_features/server_arguments.mdx +++ b/docs_new/docs/advanced_features/server_arguments.mdx @@ -334,6 +334,12 @@ Please consult the documentation below and [server_args.py](https://github.com/s `None` Type: str + + `--enable-quant-communications` + Enable INT8 quantization of TP communications (Supported only for NPU for Qwen3 series). + `False` + bool flag (set to enable) +