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

feat(mem_cache): page-major (layer-major within a page) KV/state layout (#29533)

Browse Source 
Co-authored-by: lch1475369 <lch1475369@gmail.com>
This commit is contained in:
Cheng Wan
2026-06-29 14:49:54 -07:00
committed by GitHub
co-authored by lch1475369
parent 6c018eb4d1
commit fc96edd297
25 changed files with 2159 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/docs/advanced_features/server_arguments.mdx
+6
View File
@@ -509,6 +509,12 @@ Please consult the documentation below and [server_args.py](https://github.com/s
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>The number of tokens in a page.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`1`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Type: int</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--enable-page-major-kv-layout`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable the page-major KV layout: lay out the Mamba state and full/SWA KV caches in a page-granularity envelope (page is the outermost axis, layer-major within a page) instead of the default per-layer (layer-major) layout. Requires the Triton attention / linear-attn / Mamba backends (`--attention-backend triton`, and for hybrid models `--linear-attn-backend triton --mamba-backend triton`).</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`False`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>bool flag (set to enable)</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`--swa-full-tokens-ratio`</td>