Support fastsafetensors no-GDS loading and page-cache release (#31859)
This commit is contained in:
@@ -145,6 +145,12 @@ python -m sglang.launch_server \
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Filename pattern for per-rank shards.</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>model-rank-{rank}-part-{part}.safetensors</code></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>fastsafetensors</code></td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>enable_gds</code> (bool)</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Use GPU Direct Storage. Set to <code>false</code> when the host does not provide the NVIDIA GPUDirect Storage kernel driver, such as in a gVisor sandbox.</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>true</code></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>bitsandbytes</code></td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>qlora_adapter_name_or_path</code> (str)</td>
|
||||
@@ -200,7 +206,7 @@ Top-level arguments that tune how safetensors weights are read, independent of `
|
||||
</tr>
|
||||
<tr>
|
||||
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}><code>--weight-loader-drop-cache-after-load</code></td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Call <code>posix_fadvise(DONTNEED)</code> on each safetensors shard after loading it, freeing page cache.</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Call <code>posix_fadvise(DONTNEED)</code> after successfully loading each shard, freeing page cache. Supported by the standard safetensors and <code>fastsafetensors</code> loaders.</td>
|
||||
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>off</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
||||
Reference in New Issue
Block a user