[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>
This commit is contained in:
2026-10-19 02:19:03 +07:00
co-authored by Hinata
parent 54a396586e
commit 2b544b7ba0
353 changed files with 29 additions and 121269 deletions
-102
View File
@@ -7,112 +7,10 @@ names so that :class:`ReasoningParserManager` and
:class:`ToolParserManager` can load them lazily.
"""
from vllm.parser.deepseek_v4 import DeepSeekV4Parser
from vllm.parser.deepseek_v32 import DeepSeekV32Parser
from vllm.parser.deepseek_v41 import DeepSeekV41Parser
from vllm.parser.engine.adapters import make_adapters
from vllm.parser.gemma4 import Gemma4Parser
from vllm.parser.glm47_moe import Glm47MoeParser
from vllm.parser.granite import GraniteParser
from vllm.parser.granite_thinking import GraniteThinkingParser
from vllm.parser.inkling import InklingParser
from vllm.parser.kimi_k2 import KimiK2Parser
from vllm.parser.mimo import MiMoParser
from vllm.parser.minimax_m2 import MinimaxM2Parser
from vllm.parser.minimax_m3 import MinimaxM3Parser
from vllm.parser.mistral import MistralParser
from vllm.parser.nemotron_v3 import NemotronV3Parser
from vllm.parser.plamo3 import Plamo3Parser
from vllm.parser.qwen3 import Qwen3Parser
from vllm.parser.seed_oss import SeedOssParser
from vllm.parser.step3p5 import Step3p5Parser
(
DeepSeekV32ParserReasoningAdapter,
DeepSeekV32ParserToolAdapter,
) = make_adapters(DeepSeekV32Parser)
(
DeepSeekV4ParserReasoningAdapter,
DeepSeekV4ParserToolAdapter,
) = make_adapters(DeepSeekV4Parser)
(
DeepSeekV41ParserReasoningAdapter,
DeepSeekV41ParserToolAdapter,
) = make_adapters(DeepSeekV41Parser)
(
MinimaxM2ParserReasoningAdapter,
MinimaxM2ParserToolAdapter,
) = make_adapters(MinimaxM2Parser)
(
MinimaxM3ParserReasoningAdapter,
MinimaxM3ParserToolAdapter,
) = make_adapters(MinimaxM3Parser)
(
Gemma4ParserReasoningAdapter,
Gemma4ParserToolAdapter,
) = make_adapters(Gemma4Parser)
(
GraniteParserReasoningAdapter,
GraniteParserToolAdapter,
) = make_adapters(GraniteParser)
(
GraniteThinkingParserReasoningAdapter,
GraniteThinkingParserToolAdapter,
) = make_adapters(GraniteThinkingParser)
(
NemotronV3ParserReasoningAdapter,
NemotronV3ParserToolAdapter,
) = make_adapters(NemotronV3Parser)
(
Qwen3ParserReasoningAdapter,
Qwen3ParserToolAdapter,
) = make_adapters(Qwen3Parser)
(
MiMoParserReasoningAdapter,
MiMoParserToolAdapter,
) = make_adapters(MiMoParser)
(
SeedOssParserReasoningAdapter,
SeedOssParserToolAdapter,
) = make_adapters(SeedOssParser)
(
Step3p5ParserReasoningAdapter,
Step3p5ParserToolAdapter,
) = make_adapters(Step3p5Parser)
(
Glm47MoeParserReasoningAdapter,
Glm47MoeParserToolAdapter,
) = make_adapters(Glm47MoeParser)
(
KimiK2ParserReasoningAdapter,
KimiK2ParserToolAdapter,
) = make_adapters(KimiK2Parser)
(
InklingParserReasoningAdapter,
InklingParserToolAdapter,
) = make_adapters(InklingParser)
(
MistralParserReasoningAdapter,
MistralParserToolAdapter,
) = make_adapters(MistralParser)
(
Plamo3ParserReasoningAdapter,
Plamo3ParserToolAdapter,
) = make_adapters(Plamo3Parser)