Clarify supported context length in docs (#21)

- update: clearify supported context length in docs (7d718af0cb9fc1c12440bc9912e5abcb42067873)
- update (67e71adcb7d24eadc6f88a02c6665ef3634fe197)

docs/sglang_deploy_guide.md

@@ -27,9 +27,11 @@ The deployment process is illustrated below using MiniMax-M2.1 as an example.
 
 The following are recommended configurations; actual requirements should be adjusted based on your use case:
 
-- 4x 96GB GPUs: Supported context length of up to 400K tokens.
+- **96G x4** GPU: Supports a total KV Cache capacity of 400K tokens.
 
-- 8x 144GB GPUs: Supported context length of up to 3M tokens.
+- **144G x8** GPU: Supports a total KV Cache capacity of up to 3M tokens.
+
+> **Note**: The values above represent the total aggregate hardware KV Cache capacity. The maximum context length per individual sequence remains **196K** tokens.
 
 ## Deployment with Python
 

docs/sglang_deploy_guide_cn.md

@@ -27,9 +27,11 @@
 
 以下为推荐配置，实际需求请根据业务场景调整：
 
-- 96G x4 GPU：支持 40 万 token 的总上下文。
+- **96G x4 GPU**：总 KV Cache 容量支持 40 万 token。
 
-- 144G x8 GPU：支持长达 300 万 token 的总上下文。
+- **144G x8 GPU**：总 KV Cache 容量支持高达 300 万 token。
+
+> **注**：以上数值为硬件支持的最大并发缓存总量，模型单序列（Single Sequence）长度上限仍为 196k。
 
 ## 使用 Python 部署
 

docs/vllm_deploy_guide.md

@@ -26,9 +26,11 @@ The deployment process is illustrated below using MiniMax-M2.1 as an example.
 
 The following are recommended configurations; actual requirements should be adjusted based on your use case:
 
-- 4x 96GB GPUs: Supported context length of up to 400K tokens.
+- **96G x4** GPU: Supports a total KV Cache capacity of 400K tokens.
 
-- 8x 144GB GPUs: Supported context length of up to 3M tokens.
+- **144G x8** GPU: Supports a total KV Cache capacity of up to 3M tokens.
+
+> **Note**: The values above represent the total aggregate hardware KV Cache capacity. The maximum context length per individual sequence remains **196K** tokens.
 
 ## Deployment with Python
 

docs/vllm_deploy_guide_cn.md

@@ -26,9 +26,11 @@
 
 以下为推荐配置，实际需求请根据业务场景调整：
 
-- 96G x4 GPU：支持 40 万 token 的总上下文。
+- **96G x4 GPU**：总 KV Cache 容量支持 40 万 token。
 
-- 144G x8 GPU：支持长达 300 万 token 的总上下文。
+- **144G x8 GPU**：总 KV Cache 容量支持高达 300 万 token。
+
+> **注**：以上数值为硬件支持的最大并发缓存总量，模型单序列（Single Sequence）长度上限仍为 196k。
 
 ## 使用 Python 部署