MOVZXandHinata
2066d3143f
- Remove Anthropic, Cohere, SageMaker, decisions, structured-decisions, rl, render-launcher and batch entrypoints; keep scale-out token routes - Drop the Swagger static bundle and the /docs, /redoc routes - Delete device-keyed tuning configs for fused_moe, quant utils, mamba select-state and helion; no sm86 entry ever existed for any of them - Remove ten unused rope variants plus the fbgemm_fp8 and fp_quant quantizers and their config, metrics and loader plumbing - Cut the CPU device build: csrc/cpu, cpu_extension.cmake, cpu requirements and the setup.py cpu target path - Delete 29 environment variables nothing reads and 14 chat-template fallbacks for models this fork no longer registers - Remove nine dead CUDA ops (deepseek_v4, kimi_k3, minimax, muse_spark, dsv3 gemm) with their kernels, bindings, wrappers and CMake entries - Delete the connector test suites that targeted removed connectors - Cut the Mistral tokenizer and parser stack, its tests, and the mistral_common and ijson dependency pins - Restore the Qwen4Exp registry rows and nvidia/mtp.py that an earlier cut deleted while keeping the model tree Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
56 lines
1.6 KiB
Python
56 lines
1.6 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import warnings
|
|
|
|
from vllm.entrypoints.launchers.api_server.app_state import init_app_state
|
|
from vllm.entrypoints.launchers.api_server.entry import (
|
|
build_and_serve,
|
|
build_async_engine_client,
|
|
build_async_engine_client_from_engine_args,
|
|
run_server,
|
|
run_server_worker,
|
|
)
|
|
from vllm.entrypoints.launchers.api_server.routers import register_api_routers
|
|
from vllm.entrypoints.launchers.app import build_app
|
|
from vllm.entrypoints.launchers.launcher import (
|
|
create_server_socket,
|
|
create_server_unix_socket,
|
|
setup_server,
|
|
validate_api_server_args,
|
|
)
|
|
|
|
warnings.warn(
|
|
"`vllm.entrypoints.openai.api_server` is deprecated and will likely be"
|
|
"unsupported in a future version. Use the corresponding function from "
|
|
"`vllm.entrypoints.launchers` instead.",
|
|
DeprecationWarning,
|
|
stacklevel=1,
|
|
)
|
|
|
|
|
|
__all__ = [
|
|
"build_async_engine_client",
|
|
"build_async_engine_client_from_engine_args",
|
|
"build_app",
|
|
"init_app_state",
|
|
"create_server_socket",
|
|
"create_server_unix_socket",
|
|
"validate_api_server_args",
|
|
"setup_server",
|
|
"build_and_serve",
|
|
"run_server",
|
|
"run_server_worker",
|
|
"register_api_routers",
|
|
]
|
|
|
|
if __name__ == "__main__":
|
|
warnings.warn(
|
|
"The `python -m vllm.entrypoints.openai.api_server` command is deprecated "
|
|
"and may be removed in a future release. Please use `vllm server` instead.",
|
|
DeprecationWarning,
|
|
stacklevel=1,
|
|
)
|
|
from vllm.entrypoints.launchers.api_server.entry import main
|
|
|
|
main()
|