[BugFix] Fix ACLgraph bug in Qwen3_32b_int8 case (#3204)
### What this PR does / why we need it? 1. Solved the issue where sizes capture failed for the Qwen3-32b-int8 model when aclgraph, dp1, and tp4 were enabled. 2. Added the exception thrown when sizes capture fails and provided a solution 3. Add this common problem to the FAQ doc ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? ut - vLLM version: v0.10.2 - vLLM main: https://github.com/vllm-project/vllm/commit/releases/v0.11.0 Signed-off-by: lilinsiman <lilinsiman@gmail.com>
This commit is contained in:
@@ -3418,10 +3418,23 @@ class NPUModelRunner(LoRAModelRunnerMixin):
|
||||
aclgraph_runtime_mode = aclgraph_mode.mixed_mode()
|
||||
|
||||
compilation_cases = list(reversed(self.aclgraph_batch_sizes))
|
||||
self._capture_aclgraphs(
|
||||
compilation_cases,
|
||||
aclgraph_runtime_mode=aclgraph_runtime_mode,
|
||||
uniform_decode=False)
|
||||
|
||||
try:
|
||||
self._capture_aclgraphs(
|
||||
compilation_cases,
|
||||
aclgraph_runtime_mode=aclgraph_runtime_mode,
|
||||
uniform_decode=False)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"ACLgraph sizes capture fail: {type(e).__name__}:\n"
|
||||
"ACLgraph has insufficient available streams to capture the configured number of sizes. "
|
||||
"Please verify both the availability of adequate streams and the appropriateness of the configured size count.\n\n"
|
||||
"Recommended solutions:\n"
|
||||
"1. Manually configure the compilation_config parameter "
|
||||
"with a reduced set of sizes: '{\"cudagraph_capture_sizes\":[size1, size2, size3, ...]}'.\n"
|
||||
"2. Utilize ACLgraph's full graph mode as an alternative to the piece-wise approach.\n\n"
|
||||
f"{str(e)}")
|
||||
raise
|
||||
|
||||
if aclgraph_mode.decode_mode() == CUDAGraphMode.FULL and \
|
||||
aclgraph_mode.separate_routine():
|
||||
|
||||
Reference in New Issue
Block a user