[Executor]CUDAGraph support Speculate Decode (#4258)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled

* [Executor]CUDAGraph support Speculate Decode

* fix problem

* solve problem

* fix

* fast compile

* CUDAGraph + mtp support eb5(only target model)

* Revert "fast compile"

This reverts commit 3cfe8373ed.

* fix precommit

* solve comment

* fix comment about #pragram unroll

---------

Co-authored-by: gongshaotian <gstain5555@outlook.com>
Co-authored-by: gongshaotian <gstian5555@outlook.com>
This commit is contained in:
Jundong Liu
2025-10-13 15:21:41 +08:00
committed by GitHub
parent 07db281647
commit 0b7a5778ab
16 changed files with 265 additions and 134 deletions

View File

@@ -133,6 +133,7 @@ class ForwardMeta:
"shape": obj.shape,
"dtype": str(obj.dtype),
"place": str(obj.place),
"content": obj if obj.numel() < 70 else "Too big to show",
}
return tensor_info
elif isinstance(obj, (list, tuple)):