feat(mem_cache): page-major (layer-major within a page) KV/state layout (#29533)
Co-authored-by: lch1475369 <lch1475369@gmail.com>
This commit is contained in:
@@ -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>
|
||||
|
||||
Reference in New Issue
Block a user