A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 9, 19:30 UTC
[Frontend] add prompt_cache_key for openresponses (#32824)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Jan 22, 2026 at 19:34 UTC
841d53aaa8d674f2c9f72503e77f75e5ffa79c71
1 file changed
+8
vllm/entrypoints/openai/responses/protocol.py
+8
@@ -173,6 +173,14 @@ class ResponsesRequest(OpenAIBaseModel):
173
user: str | None = None
174
skip_special_tokens: bool = True
175
include_stop_str_in_output: bool = False
176
+ prompt_cache_key: str | None = Field(
177
+ default=None,
178
+ description=(
179
+ "A key that was used to read from or write to the prompt cache."
180
+ "Note: This field has not been implemented yet "
181
+ "and vLLM will ignore it."
182
+ ),
183
+ )
184
185
# --8<-- [start:responses-extra-params]
186
request_id: str = Field(