A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 05:00 UTC
[CI] Enable mypy import following for vllm/v1/kv_offload (#34639)
Signed-off-by: Aneesh Puttur <aneeshputtur@gmail.com>
Aneesh Puttur committed
Feb 16, 2026 at 20:58 UTC
0b5f9b720451dab9d2fcba2a697fa59e0c0add01
1 file changed
-2
tools/pre_commit/mypy.py
-2
@@ -30,8 +30,6 @@ SEPARATE_GROUPS = [
30
# v0 related
31
"vllm/lora",
32
"vllm/model_executor",
33
- # v1 related
34
- "vllm/v1/kv_offload",
33
]
34
35
# TODO(woosuk): Include the code from Megatron and HuggingFace.