Files
MOVZXandHinata 2b544b7ba0 [Mini-VLLM] Cut dead subsystems across serving, connectors, parsers
- Remove P/D transfer connectors: nixl, nixl_chat, mooncake x2, hf3fs,
  moriio, hisparse, example and hidden-states connectors
- Reduce weight_transfer to the base API used by model loading
- Remove kv_offload tiering, simple_kv_offload, ec cpu/example,
  snapshot command, engine snapshot server
- Remove transformers model fallback, dsv4 tokenizers, dead platforms
  cpu/tpu/xpu, flashmla third_party, dsa, megamoe/flydsl, dead attn
  ops, dead layers (short_conv, fused_embed_norm, indexer_topk,
  relu2 gemma_ar, lightning_attn, minimax_rms_norm), gemm_rs_ar
- Keep MoE LoRA op (imported eagerly by punica_gpu); drop fp8 variant
- Rebuild parser hubs around Qwen3 adapters only (36 dead adapters)
- Remove dead tests with the code they covered

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 02:19:03 +07:00

45 lines
1.1 KiB
Python

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm.tool_parsers.abstract_tool_parser import (
ToolParser,
ToolParserManager,
)
__all__ = ["ToolParser", "ToolParserManager"]
"""
Register a lazy module mapping.
Example:
ToolParserManager.register_lazy_module(
name="kimi_k2",
class_name="KimiK2ToolParser",
)
"""
_TOOL_PARSERS_TO_REGISTER = {
"qwen3_coder": (
"qwen3_engine_tool_parser",
"Qwen3EngineToolParser",
),
# TODO: Qwen2.5/QwQ/Qwen3 JSON tool calls. Aliased to `hermes` for now;
# a dedicated parser should treat the template's newline before and
# between `<tool_call>` blocks as framing, as the Rust frontend does.
"qwen3_xml": (
"qwen3_engine_tool_parser",
"Qwen3EngineToolParser",
),
}
def register_lazy_tool_parsers():
for name, (file_name, class_name) in _TOOL_PARSERS_TO_REGISTER.items():
module_path = f"vllm.tool_parsers.{file_name}"
ToolParserManager.register_lazy_module(name, module_path, class_name)
register_lazy_tool_parsers()