[CI] Upgrade vllm to newest commit (#3182)
### What this PR does / why we need it? Upgrade vLLM to newest commit - Fix the aclgraph doesn't work problem, caused by24fab45d96- Fix PoolerOutput import error, caused by755ed7b05b- Fix the aclgraph weight load error to keep the same with torchair fix.4492e3a554### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? All test should pass - vLLM version: v0.10.2 - vLLM main:52d0cb8458--------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
@@ -209,6 +209,11 @@ class NPUPlatform(Platform):
|
||||
# set cudaprah sizes before extending `compilation_config.splitting_ops`
|
||||
vllm_config._set_cudagraph_sizes()
|
||||
|
||||
# TODO: Full graph is fully supported later, and the default value will be set to full graph.
|
||||
if not vllm_version_is("v0.10.2"):
|
||||
if compilation_config.cudagraph_mode == CUDAGraphMode.FULL_AND_PIECEWISE:
|
||||
compilation_config.cudagraph_mode = CUDAGraphMode.PIECEWISE
|
||||
|
||||
if compilation_config.cudagraph_mode == CUDAGraphMode.NONE:
|
||||
compilation_config.level = CompilationLevel.NO_COMPILATION
|
||||
# TODO: Currently MLA does not support FULL_DECODE_ONLY, remove the second condition
|
||||
|
||||
Reference in New Issue
Block a user