xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-06 07:07:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add SSM and Hybrid Models Test

Browse Source 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Tyler Michael Smith 2025-03-15 17:26:01 +00:00
parent 61c6a5a796
commit 696245c2fc
2 changed files with 571 additions and 566 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1135
.buildkite/test-pipeline.yaml
View File

File diff suppressed because it is too large Load Diff

2
vllm/model_executor/models/bamba.py
View File

@ -38,8 +38,6 @@ from .utils import (is_pp_missing_parameter,
make_empty_intermediate_tensors_factory, make_layers,
maybe_prefix)
KVCache = Tuple[torch.Tensor, torch.Tensor]
class BambaMLP(nn.Module):