Enable validated prefix caching and record DGX Spark optimization benchmarks

patches/fix_mamba_prefix_blocks.py

@@ -0,0 +1,28 @@
+# Derived from blazux/qwen3.8-Flash-DGX, Copyright 2026 blazux.
+# SPDX-License-Identifier: Apache-2.0
+"""Pinned-nightly Mamba prefix alignment fix, following blazux's diagnosis.
+
+Reference: https://github.com/blazux/qwen3.8-Flash-DGX/blob/main/src/patch_mamba_block_size.py
+Do not silently apply to a different source layout.
+"""
+import ast
+import sys
+from pathlib import Path
+
+root = Path(sys.argv[1]) / 'vllm'
+changes = [
+    (root / 'v1/worker/gpu/model_states/mamba_hybrid.py',
+     '(new_req_data.num_computed_tokens - 1) // self.cache_config.block_size',
+     '(new_req_data.num_computed_tokens - 1)\n'
+     '                // (self.cache_config.mamba_block_size or self.cache_config.block_size)'),
+    (root / 'v1/core/sched/scheduler.py',
+     '        block_size = self.cache_config.block_size\n        # The last block-aligned',
+     '        block_size = self.block_size\n        # The last block-aligned'),
+]
+for path, before, after in changes:
+    source = path.read_text()
+    assert source.count(before) == 1, f'Unexpected upstream layout: {path}'
+    updated = source.replace(before, after)
+    ast.parse(updated)
+    path.write_text(updated)
+print('Mamba prefix block alignment patched')