EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

provide an e2e guide for execute duration profiling (#1113)

Browse Source 
### What this PR does / why we need it?
provide an e2e guide for execute duration profiling


Signed-off-by: depeng1994 <depengzhang@foxmail.com>
This commit is contained in:
depeng1994
2025-06-11 10:02:11 +08:00
committed by GitHub
parent 7bdc606677
commit 860a5ef7fd
2 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_ascend/worker/model_runner_v1.py
View File

@@ -1317,8 +1317,8 @@ class NPUModelRunner(LoRAModelRunnerMixin):
for tag, duration in durations.items()
]
captured_name = "Decode" if self.attn_state == AscendAttentionState.DecodeOnly else "Prefill"
print(f"Profile execute duration [{captured_name}]:",
" ".join(dr_str))
logger.info("Profile execute duration [%s]:%s", captured_name,
" ".join(dr_str))
return model_runner_output