Files
MOVZXandHinata 61fbe0b865 [Mini-VLLM] Remove unreferenced definitions found by static scan
A symbol scan over every tracked file found 123 top-level definitions in
vllm/ with zero references, including references inside strings. All of
them came from features this fork deleted earlier.

- Delete dead attention helpers: MLADCPManager, split_prefill_chunks, the
  reshape helpers, compute_varlen_chunk_metadata, the LINEAR backend's
  unused BailingLinearAttentionBackend, and the sparse flash-attn entry
  points.
- Delete the CPU and AMX op wrappers from _custom_ops.py: cpu_mla_decode,
  cpu_mla_extend, cpu_mla_get_scheduler_metadata,
  gather_mla_context_cache_cpu.
- Delete dead quantization helpers: awq_pack, gptq_pack,
  gptq_quantize_weights, get_and_maybe_dequant_weights,
  marlin_quant_fp8_torch, the rand_marlin_weight_*_like pair,
  ocp_mx_weight_dtype_and_rows, get_fp8_block_weight_scale,
  input_to_float8.
- Delete dead model helpers: resolve_visual_encoder_outputs,
  run_dp_sharded_vision_model, fast_topk, get_layer_index,
  is_pp_missing_parameter, skip_spec_layers, KimiK3MergedQKVGateLinear,
  selective_scan_fn, causal_conv1d_update_torch.
- Delete dead utils: format_kib, format_mib, chunk_list, prev_power_of_2,
  split_host_port, join_host_port, make_zmq_path, make_async_with_semaphore,
  is_meta_module, is_non_overlapping_and_dense, supports_xpu_graph,
  create_kv_caches_with_random*, and the unused has_* capability probes.
- Delete the unreachable deep-gemm mega-MoE warmup path, which imported
  vllm.models.deepseek_v4.nvidia.model and vllm.models.kimi_k3.nvidia.model,
  neither of which exists anymore.
- Drop the imports and the two now-empty guards left behind.

Verified statically: every changed file compiles, no unused import
remains, and no deleted name is referenced in vllm, tests or csrc. The
runtime gates still need the Python environment rebuilt.

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 21:39:56 +07:00

42 lines
1.4 KiB
Python

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from collections.abc import Iterable, Iterator
from torch import fx
from torch._higher_order_ops.auto_functionalize import auto_functionalized
from torch._ops import OpOverload, OpOverloadPacket
from torch.fx.node import Target
def is_func(node: fx.Node, target: Target) -> bool:
return bool(node.op == "call_function" and node.target == target)
# Returns the first auto_functionalized node with the given op (if it exists)
def find_auto_fn_maybe(nodes: Iterable[fx.Node], op: OpOverload) -> fx.Node | None:
for node in nodes:
if is_func(node, auto_functionalized) and node.args[0] == op: # noqa
return node
return None
# An auto-functionalization-aware utility for finding nodes with a specific op
# Also handles op overload packets and finds all overloads
def find_op_nodes(
op: OpOverload | OpOverloadPacket, graph: fx.Graph
) -> Iterator[fx.Node]:
if isinstance(op, OpOverloadPacket):
for overload in op.overloads():
overload_op = getattr(op, overload)
yield from find_op_nodes(overload_op, graph)
return
assert isinstance(op, OpOverload)
yield from graph.find_nodes(op="call_function", target=op)
for n in graph.find_nodes(op="call_function", target=auto_functionalized):
if n.args[0] == op:
yield n