feat: spec decode with draft models (#24322)

Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>

feat: spec decode with draft models (#24322)
Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
4a5299c9 · Tomas Ruiz · GitHub · 73f2a81c · 4a5299c9
Unverified Commit 4a5299c9 authored Jan 19, 2026 by Tomas Ruiz Committed by GitHub Jan 19, 2026
Show whitespace changes
Inline Side-by-side

Showing with 2 additions and 2 deletions

vllm/v1/worker/utils.py vllm/v1/worker/utils.py +2 -2

No files found.
--- a/vllm/v1/worker/utils.py
+++ b/vllm/v1/worker/utils.py
@@ -352,7 +352,7 @@ def bind_kv_cache(
                pass
            else:
                raise NotImplementedError
-        layer_name = layer_names[0]
+        for layer_name in layer_names:
            runner_kv_caches.append(kv_caches[layer_name])
    # Bind kv_caches to forward context