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

[v0.11.0-dev][CI] Fix ngram lacking of input arg dummy_compute_logits error (#4648)

Browse Source 
### What this PR does / why we need it?
Fix ngram lacking of input arg `dummy_compute_logits` error

### How was this patch tested?
CI passed with existing test.

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-12-03 09:22:07 +08:00
committed by GitHub
parent 865f1f7fc8
commit b6d63bbd52
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm_ascend/spec_decode/interface.py
View File

@@ -35,7 +35,8 @@ class Proposer:
num_reqs: int = 0,
num_tokens_across_dp: Optional[torch.Tensor] = None,
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
batch_descriptor=None):
batch_descriptor=None,
dummy_compute_logits=lambda hidden_states: None):
"""Called by dummy_run in modle_runner"""
raise NotImplementedError

3
vllm_ascend/spec_decode/ngram_proposer.py
View File

@@ -26,7 +26,8 @@ class NgramProposer(VllmNgramProposer, Proposer):
num_reqs=None,
num_tokens_across_dp=None,
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
batch_descriptor=None):
batch_descriptor=None,
dummy_compute_logits=lambda hidden_states: None):
pass
def generate_token_ids(self,