Update vllm/v1/worker/gpu_model_runner.py

Co-authored-by: Cody Yu <[email protected]> Signed-off-by: Chen Zhang <[email protected]>
vllm-project · Jan 14, 2025 · 97176da · 97176da
1 parent f79dff2
commit 97176da
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/vllm/v1/worker/gpu_model_runner.py b/vllm/v1/worker/gpu_model_runner.py
@@ -858,7 +858,7 @@ def capture_model(self) -> None:
 
     def initialize_kv_cache(self, kv_cache_config: KVCacheConfig) -> None:
         if len(kv_cache_config.groups) > 1:
-            raise NotImplementedError("Multiple groups are not supported yet.")
+            raise NotImplementedError("Hybrid kv-cache groups are not supported yet.")
 
         kv_caches: Dict[str, torch.Tensor] = {}