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

[Cleanup] Remove unused attn_metadata parameter from Proposer classes (#4862)

Browse Source 
The `attn_metadata` is not used by any draft proposer, so we can remove
it.


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
This commit is contained in:
Jade Zheng
2025-12-15 21:21:38 +08:00
committed by GitHub
parent a9625851ef
commit c064d11fd7
7 changed files with 1 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/worker/model_runner_v1.py
View File

@@ -1383,7 +1383,7 @@ class NPUModelRunner(GPUModelRunner):
draft_token_ids = self.drafter.generate_token_ids(
valid_sampled_token_ids, sampling_metadata, scheduler_output,
spec_decode_metadata, positions, num_scheduled_tokens,
hidden_states, attn_metadata, aux_hidden_states)
hidden_states, aux_hidden_states)
return draft_token_ids
def _select_moe_comm_method(self,