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, 08:30 UTC
[CI] add missing argument (#18694)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
May 26, 2025 at 15:22 UTC
4ea62c0ea0ff067853f454003d1bddeacc3629a3
1 file changed
+3
-2
tests/runai_model_streamer_test/test_weight_utils.py
+3
-2
@@ -23,10 +23,11 @@ def test_runai_model_loader():
23
runai_model_streamer_tensors = {}
24
hf_safetensors_tensors = {}
25
26
- for name, tensor in runai_safetensors_weights_iterator(safetensors):
26
+ for name, tensor in runai_safetensors_weights_iterator(
27
+ safetensors, True):
28
runai_model_streamer_tensors[name] = tensor
29
29
- for name, tensor in safetensors_weights_iterator(safetensors):
30
+ for name, tensor in safetensors_weights_iterator(safetensors, True):
31
hf_safetensors_tensors[name] = tensor
32
33
assert len(runai_model_streamer_tensors) == len(hf_safetensors_tensors)