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

[Bugfix] fix resource are insufficient when pcp and piecewise (#5377)

Browse Source 
### What this PR does / why we need it?
Resolving the issue of insufficient resources during service operation
when PCP is enabled in a piecewise scenario.

When enabling PCP and executing in piecewise mode, the curl request
fails due to insufficient resources, resulting in the error message "The
resources are insufficient." Through profiling analysis, it was found
that the PCP communication domain also occupies streams and consumes
resources. Therefore, when updating aclgraph sizes, the PCP
communication domain needs to be taken into account.

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: release/v0.13.0
- vLLM main:
bc0a5a0c08

---------

Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
This commit is contained in:
weiguihua2
2026-01-07 15:39:52 +08:00
committed by GitHub
parent 4f9808002b
commit 2b8a9ce8bd
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
vllm_ascend/utils.py
View File

@@ -491,6 +491,9 @@ def update_aclgraph_sizes(vllm_config: VllmConfig) -> None:
# TODO: Find out whether we need to solve allreduce function # TODO: Find out whether we need to solve allreduce function
MAX_CAPTURE_SIZE = 1800 MAX_CAPTURE_SIZE = 1800
# enable pcp or dcp will add new communication and consume additional approximately less than 100 streams
CP_ADDITIONAL_STREAM_NUM = 100
# Store original configuration and temporarily clear it # Store original configuration and temporarily clear it
compilation_config = vllm_config.compilation_config compilation_config = vllm_config.compilation_config
original_sizes, compilation_config.cudagraph_capture_sizes = \ original_sizes, compilation_config.cudagraph_capture_sizes = \
@@ -547,6 +550,12 @@ def update_aclgraph_sizes(vllm_config: VllmConfig) -> None:
"Calculated maximum supported batch sizes for ACL graph: %s", "Calculated maximum supported batch sizes for ACL graph: %s",
max_num_batch_sizes) max_num_batch_sizes)
else: else:
# enable pcp or dcp will add new communication and consume additional approximately less than 100 streams
if parallel_config.prefill_context_parallel_size > 1:
MAX_CAPTURE_SIZE = MAX_CAPTURE_SIZE - CP_ADDITIONAL_STREAM_NUM
if parallel_config.decode_context_parallel_size > 1:
MAX_CAPTURE_SIZE = MAX_CAPTURE_SIZE - CP_ADDITIONAL_STREAM_NUM
# The above describes an empirical formula applicable to the A2 hardware. # The above describes an empirical formula applicable to the A2 hardware.
# Under this configuration, HCCL employs the FFTS+ method for execution unfolding, # Under this configuration, HCCL employs the FFTS+ method for execution unfolding,
# which adds only 1 concurrent stream without consuming collective communication execution unfolding streams. # which adds only 1 concurrent stream without consuming collective communication execution unfolding streams.