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 15, 01:00 UTC
[bugfix] fix syntax warning caused by backslash (#21251)
Jiayi Yan committed
Jul 21, 2025 at 01:12 UTC
7ba34b1241ada58f8212f350a8b17382cb412cf2
2 files changed
+2
-2
examples/offline_inference/neuron_eagle.py
+1
-1
@@ -54,7 +54,7 @@ def main():
54
for output in outputs:
55
prompt = output.prompt
56
generated_text = output.outputs[0].text
57
- print(f"Prompt: {prompt!r}, \n\n\n\ Generated text: {generated_text!r}")
57
+ print(f"Prompt: {prompt!r}, \n\n\n Generated text: {generated_text!r}")
58
59
60
if __name__ == "__main__":
tests/v1/kv_connector/unit/test_nixl_connector.py
+1
-1
@@ -341,7 +341,7 @@ def test_abort_timeout_on_prefiller(monkeypatch, distributed_executor_backend):
341
Test lifecycle of an aborted Remote Prefill request hitting the timeout.
342
-----> P
343
| {process request}
344
- <-\--- | {result is NOT delivered, eg proxy is down}
344
+ <-/--- | {result is NOT delivered, eg proxy is down}
345
|
346
|
347
| {eventually free blocks}