From d1a83a72f7c4beb2d9ed3587bbe0ee58d2869551 Mon Sep 17 00:00:00 2001 From: rjg-lyh <83491835+rjg-lyh@users.noreply.github.com> Date: Tue, 24 Mar 2026 19:36:34 +0800 Subject: [PATCH] [doc] add enable_sparse_c8 option in configuration options (#7600) ### What this PR does / why we need it? This PR adds enable_sparse_c8 option in configuration options - vLLM version: v0.18.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ed359c497a728f08b5b41456c07a688ccd510fbc Signed-off-by: rjg-lyh <1318825571@qq.com> --- docs/source/user_guide/configuration/additional_config.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/source/user_guide/configuration/additional_config.md b/docs/source/user_guide/configuration/additional_config.md index d388b837..f0a7a8dd 100644 --- a/docs/source/user_guide/configuration/additional_config.md +++ b/docs/source/user_guide/configuration/additional_config.md @@ -44,6 +44,7 @@ The following table lists additional configuration options available in vLLM Asc | `pa_shape_list` | list | `[]` | The custom shape list of page attention ops. | | `enable_kv_nz` | bool | `False` | Whether to enable KV cache NZ layout. This option only takes effects on models using MLA (e.g., DeepSeek). | | `layer_sharding` | dict | `{}` | Configuration options for Layer Sharding Linear | +| `enable_sparse_c8` | bool | `False` | Whether to enable KV cache C8 in DSA models (e.g., DeepSeekV3.2 and GLM5). Not supported on A5 devices now | The details of each configuration option are as follows: