[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
@@ -46,14 +46,6 @@ def init_entrypoints_middleware(
app.add_middleware(ScalingMiddleware)
if "realtime" in supported_tasks:
# Add WebSocket metrics middleware
from vllm.entrypoints.speech_to_text.realtime.metrics import (
WebSocketMetricsMiddleware,
)
app.add_middleware(WebSocketMetricsMiddleware)
if envs.VLLM_DEBUG_LOG_API_SERVER_RESPONSE:
logger.warning(
"CAUTION: Enabling log response in the API Server. "