[Mini-vLLM] Cut dead subsystems: models, entrypoints, backends, utils, tests

- Drop dead model modules, keeping files live imports require
- Remove anthropic, cohere, codegen entrypoints and batch STT modes
- Delete unused attention backends, MoE experts, and NPU/XPU util leaves
- Strip dead third_party trees and ROCm leaves with no CUDA path
- Remove mooncake EC connectors: dependency missing since branch base
- Re-audit verified by full import sweep and Qwen3.5 smoke test

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-10-19 00:20:48 +07:00
co-authored by Hinata
parent 6a95f62e2f
commit 81074e94a3
940 changed files with 11 additions and 380533 deletions
@@ -1,27 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm import ModelRegistry
def register():
# Test directly passing the model
from .my_opt import MyOPTForCausalLM, MyOPTRawInputTokensForCausalLM
if "MyOPTForCausalLM" not in ModelRegistry.get_supported_archs():
ModelRegistry.register_model("MyOPTForCausalLM", MyOPTForCausalLM)
if "MyOPTRawInputTokensForCausalLM" not in ModelRegistry.get_supported_archs():
ModelRegistry.register_model(
"MyOPTRawInputTokensForCausalLM", MyOPTRawInputTokensForCausalLM
)
# Test passing lazy model
if "MyGemma2Embedding" not in ModelRegistry.get_supported_archs():
ModelRegistry.register_model(
"MyGemma2Embedding",
"vllm_add_dummy_model.my_gemma_embedding:MyGemma2Embedding",
)
if "MyLlava" not in ModelRegistry.get_supported_archs():
ModelRegistry.register_model("MyLlava", "vllm_add_dummy_model.my_llava:MyLlava")
@@ -1,19 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import torch
from vllm.model_executor.layers.rotary_embedding import RotaryEmbedding
# Register CustomRotaryEmbedding to CustomOP.
@RotaryEmbedding.register_oot
class DummyRotaryEmbedding(RotaryEmbedding):
"""Original rotary positional embedding."""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.addition_config = True
def forward_oot(self, *args, **kwargs) -> tuple[torch.Tensor, torch.Tensor]:
return super().forward_oot(*args, **kwargs)