[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
-67
View File
@@ -1,67 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Canvas-width handling and async read deferral for diffusion requests."""
from vllm.v1.core.sched.async_scheduler import AsyncScheduler
from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.core.sched.scheduler import Scheduler
from vllm.v1.outputs import DraftTokenIds
from vllm.v1.request import Request
def diffusion_canvas_width(request: Request, canvas_length: int) -> int:
"""The canvas width a diffusion request asked for, else the served one."""
params = request.sampling_params
extra = params.extra_args if params is not None else None
width = extra.get("diffusion_canvas_length") if extra else None
return int(width) if width else canvas_length
def _read_in_flight(request: Request, width: int) -> bool:
"""True when a read-only request has all its denoise steps in flight.
The request emits its canvas on the last step and ends, so a further
step is discarded.
"""
params = request.sampling_params
extra = params.extra_args if params is not None else None
if not extra or not extra.get("diffusion_read_only"):
return False
steps = extra.get("diffusion_max_steps")
if not steps:
return False
# Each in-flight denoise step holds one canvas of placeholders.
return request.num_output_placeholders >= steps * width
class DiffusionScheduler(Scheduler):
def update_draft_token_ids(self, draft_token_ids: DraftTokenIds) -> None:
for i, (req_id, token_ids) in enumerate(
zip(draft_token_ids.req_ids, draft_token_ids.draft_token_ids)
):
request = self.requests.get(req_id)
if request is None:
continue
width = diffusion_canvas_width(request, self.num_spec_tokens)
# Remove padded positions before the base scheduler validates grammar.
if len(token_ids) > width:
draft_token_ids.draft_token_ids[i] = token_ids[:width]
super().update_draft_token_ids(draft_token_ids)
class DiffusionAsyncScheduler(DiffusionScheduler, AsyncScheduler):
def schedule(self, throttle_prefills: bool = False) -> SchedulerOutput:
for request in self.running:
width = diffusion_canvas_width(request, self.num_spec_tokens)
# The placeholders are as wide as the served canvas.
if len(request.spec_token_ids) > width:
request.spec_token_ids = request.spec_token_ids[:width]
if _read_in_flight(request, width):
# Scheduler.schedule()'s max_tokens guard cannot be reached
# from a subclass. schedule() advances current_step before it
# checks decode eligibility, so current_step + 2 skips this
# call alone. max keeps a longer pipeline-parallel wait.
request.next_decode_eligible_step = max(
request.next_decode_eligible_step, self.current_step + 2
)
return super().schedule(throttle_prefills)