From d078cb72bd92139ebc86db214a73b4f8fc413906 Mon Sep 17 00:00:00 2001 From: amote-i <49533125+amote-i@users.noreply.github.com> Date: Mon, 1 Jun 2026 16:40:11 +0800 Subject: [PATCH] [NPU] [DOC] clarify Ascend NPU exclusive supported values for speculative args (#26903) --- .../ascend-npus/ascend_npu_support_features.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx index 166572491..80c5ea9fb 100644 --- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx +++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_support_features.mdx @@ -1346,7 +1346,7 @@ click [Server Arguments](../../advanced_features/server_arguments). `--speculative-moe-a2a-`
`backend` `None` - `ascend_fuseep` + `ascend_fuseep` (the only supported value on Ascend NPU) A2, A3 @@ -1358,7 +1358,7 @@ click [Server Arguments](../../advanced_features/server_arguments). `--speculative-draft-model-quantization` `None` - `unquant` + `unquant` (the only supported value for speculative decoding on Ascend NPU) A2, A3