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 5, 16:00 UTC
Fix shape comment in extract_hidden_states example (#38723)
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
Fynn Schmitt-Ulms committed
Apr 1, 2026 at 10:29 UTC
fa246d52318dadb7b6ca429d0f674a7375abe9ca
1 file changed
+1
-1
examples/offline_inference/extract_hidden_states.py
+1
-1
@@ -54,5 +54,5 @@ with tempfile.TemporaryDirectory() as tmpdirname:
54
print("Extracted token ids:", token_ids) # Matches prompt token ids
55
print(
56
"Extracted hidden states shape:", hidden_states.shape
57
- ) # [num_hidden_layers, prompt len, hidden size]
57
+ ) # [prompt len, num_hidden_layers, hidden size]
58
print("Extracted hidden states:", hidden_states)