[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:
@@ -23,8 +23,6 @@ from tests.parser.engine.replay_harness import (
|
||||
)
|
||||
from vllm.parser.abstract_parser import DelegatingParser
|
||||
from vllm.parser.engine.registered_adapters import (
|
||||
Glm47MoeParserReasoningAdapter,
|
||||
Glm47MoeParserToolAdapter,
|
||||
Qwen3ParserReasoningAdapter,
|
||||
Qwen3ParserToolAdapter,
|
||||
)
|
||||
@@ -62,11 +60,6 @@ class ByteFallbackMockTokenizer(MockTokenizer):
|
||||
# ── Model-specific DelegatingParser subclasses ───────────────────────
|
||||
|
||||
|
||||
class _Glm47Delegating(DelegatingParser):
|
||||
reasoning_parser_cls = Glm47MoeParserReasoningAdapter
|
||||
tool_parser_cls = Glm47MoeParserToolAdapter
|
||||
|
||||
|
||||
class _Qwen3Delegating(DelegatingParser):
|
||||
reasoning_parser_cls = Qwen3ParserReasoningAdapter
|
||||
tool_parser_cls = Qwen3ParserToolAdapter
|
||||
@@ -92,20 +85,6 @@ EXPECTED_REASONING = "Let me think about Samsung."
|
||||
EXPECTED_CONTENT = "삼성전자의 주가를 분석합니다."
|
||||
|
||||
_MODEL_CONFIGS = [
|
||||
pytest.param(
|
||||
{
|
||||
"<think>": 50,
|
||||
"</think>": 51,
|
||||
"<tool_call>": 60,
|
||||
"</tool_call>": 61,
|
||||
"<arg_key>": 62,
|
||||
"</arg_key>": 63,
|
||||
"<arg_value>": 64,
|
||||
"</arg_value>": 65,
|
||||
},
|
||||
_Glm47Delegating,
|
||||
id="glm47",
|
||||
),
|
||||
pytest.param(
|
||||
{
|
||||
"<think>": 50,
|
||||
@@ -165,7 +144,7 @@ class TestUfffdReasoningTransition:
|
||||
vocab = dict(_MODEL_CONFIGS[0].values[0])
|
||||
|
||||
tokenizer = ByteFallbackMockTokenizer(vocab, tokens, ufffd_ids)
|
||||
parser = _Glm47Delegating(tokenizer)
|
||||
parser = _Qwen3Delegating(tokenizer)
|
||||
deltas = replay_streaming(
|
||||
parser,
|
||||
tokens,
|
||||
|
||||
Reference in New Issue
Block a user