minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

docs(cookbook): port popular model usage guides into cookbook pages (#25813)

Browse Source 
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
This commit is contained in:
Prabhu Prakash Kagitha
2026-06-01 17:41:49 -07:00
committed by GitHub
co-authored by Claude Sonnet 4.6 zijiexia Zijie Xia
parent 5e63200064
commit 98a1b58c47
47 changed files with 1262 additions and 2154 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/advanced_features/attention_backend.mdx
+3 -3
View File
@@ -14,7 +14,7 @@ If you don't specify `--attention-backend`, SGLang makes a best effort to automa
## Support Matrix
The support matrix is split into two parts: MHA (standard attention) and MLA (multi-head latent attention). For an explanation of the key differences between MHA and MLA, please see the [SGLang documentation on DeepSeek MLA](../basic_usage/deepseek_v3#multi-head-latent-attention-mla-throughput-optimizations) and the original [DeepSeek MLA paper](https://arxiv.org/pdf/2405.04434).
The support matrix is split into two parts: MHA (standard attention) and MLA (multi-head latent attention). For an explanation of the key differences between MHA and MLA, please see the [SGLang documentation on DeepSeek MLA](/cookbook/autoregressive/DeepSeek/DeepSeek-V3#4-2-4-mla-optimizations) and the original [DeepSeek MLA paper](https://arxiv.org/pdf/2405.04434).
### MHA Backends
@@ -289,7 +289,7 @@ Multimodal attention is selected by `--mm-attention-backend`. The "MultiModal" c
<Note>
- FlashAttention 4 supports both prefill and decode on SM90 (Hopper) and SM100 (Blackwell). FA4 MLA supports `page_size = 1`; FA4 MHA requires `page_size = 128`. On SM100, this is auto-enforced by the server; on SM90, users must set `--page-size 128` manually.
- DSA is specifically designed for [DeepSeek V3.2](https://lmsys.org/blog/2025-09-29-deepseek-V32/). See the [DSA Attention Backend](#dsa-attention-backend) section and [DeepSeek V3.2 deployment guide](../basic_usage/deepseek_v32) for details.
- DSA is specifically designed for [DeepSeek V3.2](https://lmsys.org/blog/2025-09-29-deepseek-V32/). See the [DSA Attention Backend](#dsa-attention-backend) section and [DeepSeek V3.2 deployment guide](/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2) for details.
</Note>
<Warning>
@@ -455,7 +455,7 @@ Internally, the DSA backend dispatches to different sub-backends for prefill and
</tbody>
</table>
For deployment examples, see the [DeepSeek V3.2 deployment guide](../basic_usage/deepseek_v32).
For deployment examples, see the [DeepSeek V3.2 deployment guide](/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2).
### Hybrid attention (different backends for prefill vs decode) (Experimental)