EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Deprecate disable-mla (#5481)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-04-17 01:43:14 -07:00
committed by GitHub
parent 81c891111f
commit 4fb05583ef
9 changed files with 188 additions and 575 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/references/deepseek.md
View File

@@ -100,7 +100,7 @@ Overall, with these optimizations, we have achieved up to **7x** acceleration in
<img src="https://lmsys.org/images/blog/sglang_v0_3/deepseek_mla.svg" alt="Multi-head Latent Attention for DeepSeek Series Models">
</p>
**Usage**: MLA optimization is enabled by default. To disable MLA usage, use `--disable-mla`. To disable chunked prefix cache feature for mla, use `disable-chunked-prefix-cache`.
**Usage**: MLA optimization is enabled by default. To disable chunked prefix cache feature for mla, use `disable-chunked-prefix-cache`.
**Reference**: Check [Blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/#deepseek-multi-head-latent-attention-mla-throughput-optimizations) and [Slides](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/lmsys_1st_meetup_deepseek_mla.pdf) for more details.