Support fastsafetensors no-GDS loading and page-cache release (#31859)

This commit is contained in:
Nan Jiang
2026-07-31 23:12:32 +08:00
committed by GitHub
parent 5f9b0db18c
commit 89f4a80c1f
4 changed files with 131 additions and 7 deletions
@@ -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-&#123;rank&#125;-part-&#123;part&#125;.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>