[Doc] pin the version of vllm-ascend that stable running 310I Duo to v0.10.0.rc1

Signed-off-by: leo-pony <nengjunma@outlook.com>

Author: leo-pony

docs/source/faqs.md

@@ -15,7 +15,7 @@ Currently, **ONLY** Atlas A2 series(Ascend-cann-kernels-910b)，Atlas A3 series(
 - Atlas 800I A2 Inference series (Atlas 800I A2)
 - Atlas A3 Training series (Atlas 800T A3, Atlas 900 A3 SuperPoD, Atlas 9000 A3 SuperPoD)
 - Atlas 800I A3 Inference series (Atlas 800I A3)
-- [Experimental] Atlas 300I Inference series (Atlas 300I Duo)
+- [Experimental] Atlas 300I Inference series (Atlas 300I Duo). Currently for 310I Duo the stable version is vllm-ascend v0.10.0rc1.
 
 Below series are NOT supported yet:
 - Atlas 200I A2 (Ascend-cann-kernels-310b) unplanned yet

docs/source/tutorials/single_node_300i.md

@@ -3,6 +3,7 @@
 ```{note}
 1. This Atlas 300I series is currently experimental. In future versions, there may be behavioral changes around model coverage, performance improvement.
 2. Currently, the 310I series only supports eager mode and the data type is float16.
+3. The latest version has a large number of PRs for new features and models that need to be merged urgently. However, these PRs are not compatible with the 310I Duo, causing support for the 310I Duo in the main branch in breaking state. This issue is still in fixing. The current stable version for 310I Duo is vllm-ascend v0.10.0rc1.
 ```
 
 ## Run vLLM on Altlas 300I series
@@ -12,7 +13,7 @@ Run docker container:
 ```{code-block} bash
    :substitutions:
 # Update the vllm-ascend image
-export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|-310p
+export IMAGE=quay.io/ascend/vllm-ascend:v0.10.0rc1-310p
 docker run --rm \
 --name vllm-ascend \
 --device /dev/davinci0 \