anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[NPU][BugFix] Upgrade parts of ModelRunner to v0.22.0 (#4130)

Browse Source 
Signed-off-by: tanhaoan333 <tanhaoan@huawei.com>
This commit is contained in:
tanhaoan333 authored and GitHub committed 2026-06-04 03:59:26 +00:00
1 parent 800c2b8251
commit d8dc1defa7
2 files changed
+2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/platforms/npu/worker/npu_ar_model_runner.py
+1
View File
@@ -395,6 +395,7 @@ class NPUARModelRunner(OmniNPUModelRunner):
logits_indices,
spec_decode_metadata,
total_num_scheduled_tokens,
num_scheduled_tokens_compressed_list,
) = self._prepare_inputs(
scheduler_output,
num_scheduled_tokens_np,
vllm_omni/platforms/npu/worker/npu_generation_model_runner.py
+1
View File
@@ -158,6 +158,7 @@ class NPUGenerationModelRunner(OmniNPUModelRunner):
logits_indices,
spec_decode_metadata,
total_num_scheduled_tokens,
num_scheduled_tokens_compressed_list,
) = self._prepare_inputs(
scheduler_output,
num_scheduled_tokens_np,