Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions vllm/compilation/backends.py
Original file line number Diff line number Diff line change
Expand Up @@ -110,10 +110,14 @@ def compile(self,
compiled_graph = self.load(graph, example_inputs, graph_index,
runtime_shape)
if compiled_graph is not None:
if graph_index == 0:
# adds some info logging for the first graph
logger.info("Directly load the compiled graph for shape %s "
"from the cache", str(runtime_shape)) # noqa
if graph_index == num_graphs - 1:
# after loading the last graph for this shape, record the time.
# there can be multiple graphs due to piecewise compilation.
now = time.time()
elapsed = now - compilation_start_time
logger.info(
"Directly load the compiled graph(s) for shape %s "
"from the cache, took %.3f s", str(runtime_shape), elapsed)
return compiled_graph

# no compiler cached the graph, or the cache is disabled,
Expand Down