[Model] Add PW CUDA graph support for Inkling [2/N] (#48822)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai> Co-authored-by: Bugen Zhao <i@bugenzhao.com> Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com> Co-authored-by: Isotr0py <Isotr0py@outlook.com> Co-authored-by: Isotr0py <mozf@inferact.ai> Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai> Co-authored-by: Roger Wang <hey@rogerw.io> Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai> Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
co-authored by
Bugen Zhao
Giancarlo Delfin
Isotr0py
Isotr0py
Jee Jee Li
Roger Wang
Yifan Qiao
Claude Fable 5
OpenAI Codex
parent
ce65385618
commit
251f7e478e
@@ -56,7 +56,10 @@ class SpeculatorCudaGraphManager(CudaGraphManager):
|
||||
block_tables,
|
||||
attn_groups,
|
||||
kv_cache_config,
|
||||
skip_attn=(desc.cg_mode == CUDAGraphMode.PIECEWISE),
|
||||
skip_attn=(
|
||||
desc.cg_mode == CUDAGraphMode.PIECEWISE
|
||||
and not self.use_breakable_cg
|
||||
),
|
||||
)
|
||||
|
||||
return lambda cg_mode: forward_fn(
|
||||
|
||||
Reference in New Issue
Block a user