[main][Refactor] Remove with_prefill parameter from set_ascend_forward_context (#5094)
Removes the redundant `with_prefill` parameter from
`set_ascend_forward_context` to align the interface with vLLM's
`set_forward_context` for future refactoring.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
Signed-off-by: Slightwind <slightwindsec@gmail.com>
Co-authored-by: zzzzwwjj <34335947+zzzzwwjj@users.noreply.github.com>
This commit is contained in:
@@ -299,7 +299,6 @@ class MtpProposer(Proposer):
|
||||
attn_metadata,
|
||||
self.vllm_config,
|
||||
num_tokens=num_tokens,
|
||||
with_prefill=with_prefill,
|
||||
num_tokens_across_dp=num_tokens_across_dp,
|
||||
num_actual_tokens=0,
|
||||
aclgraph_runtime_mode=aclgraph_runtime_mode,
|
||||
@@ -779,7 +778,6 @@ class MtpProposer(Proposer):
|
||||
attn_metadata,
|
||||
self.vllm_config,
|
||||
num_tokens=num_input_tokens,
|
||||
with_prefill=with_prefill,
|
||||
num_tokens_across_dp=num_tokens_across_dp,
|
||||
aclgraph_runtime_mode=aclgraph_runtime_mode,
|
||||
batch_descriptor=batch_descriptor,
|
||||
|
||||
Reference in New Issue
Block a user