[Mini-VLLM] Cut non-OpenAI surfaces, dead kernels, Mistral stack

- Remove Anthropic, Cohere, SageMaker, decisions, structured-decisions,
  rl, render-launcher and batch entrypoints; keep scale-out token routes
- Drop the Swagger static bundle and the /docs, /redoc routes
- Delete device-keyed tuning configs for fused_moe, quant utils, mamba
  select-state and helion; no sm86 entry ever existed for any of them
- Remove ten unused rope variants plus the fbgemm_fp8 and fp_quant
  quantizers and their config, metrics and loader plumbing
- Cut the CPU device build: csrc/cpu, cpu_extension.cmake, cpu
  requirements and the setup.py cpu target path
- Delete 29 environment variables nothing reads and 14 chat-template
  fallbacks for models this fork no longer registers
- Remove nine dead CUDA ops (deepseek_v4, kimi_k3, minimax, muse_spark,
  dsv3 gemm) with their kernels, bindings, wrappers and CMake entries
- Delete the connector test suites that targeted removed connectors
- Cut the Mistral tokenizer and parser stack, its tests, and the
  mistral_common and ijson dependency pins
- Restore the Qwen4Exp registry rows and nvidia/mtp.py that an earlier
  cut deleted while keeping the model tree

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-10-19 17:10:56 +07:00
co-authored by Hinata
parent bd70a61c20
commit 2066d3143f
1086 changed files with 122 additions and 291919 deletions
@@ -15,7 +15,6 @@ from vllm.logger import init_logger
from vllm.sampling_params import SamplingParams
from vllm.tokenizers import TokenizerLike
from vllm.utils.import_utils import LazyLoader
from vllm.utils.mistral import is_mistral_tokenizer
from vllm.v1.structured_output.backend_types import (
StructuredOutputBackend,
StructuredOutputGrammar,
@@ -150,15 +149,12 @@ class GuidanceBackend(StructuredOutputBackend):
In that case we will remove this check from vLLM.
That kind of work is really appreciated!
"""
if is_mistral_tokenizer(tokenizer):
return tokenizer.is_tekken
# PreTrainedTokenizerFast is the same as TokenizersBackend
return isinstance(tokenizer, TokenizersBackend)
@staticmethod
def _build_ll_tokenizer(tokenizer: TokenizerLike, vocab_size: int) -> Any:
if is_mistral_tokenizer(tokenizer):
return tokenizer.llg_tokenizer
return llguidance_hf.from_tokenizer(tokenizer, max(vocab_size, len(tokenizer)))
def __post_init__(self):
+1 -20
View File
@@ -12,7 +12,6 @@ from vllm.exceptions import VLLMValidationError
from vllm.logger import init_logger
from vllm.sampling_params import SamplingParams, check_json_nesting
from vllm.utils.import_utils import LazyLoader
from vllm.utils.mistral import is_mistral_tokenizer
from vllm.v1.structured_output.backend_types import (
StructuredOutputBackend,
StructuredOutputGrammar,
@@ -46,25 +45,7 @@ class XgrammarBackend(StructuredOutputBackend):
)
full_vocab_tokenizer_info = None
if is_mistral_tokenizer(self.tokenizer):
# NOTE: ideally, xgrammar should handle this accordingly.
# refer to https://github.com/mlc-ai/xgrammar/blob/d77c0a0173ef14779c918e3be7966ba852f7910f/python/xgrammar/tokenizer_info.py#L98
stop_token_ids = [self.tokenizer.eos_token_id]
# not self.tokenizer.vocab_size as self.tokenizer.vocab
# collapses all decoded errors into a single token.
self.vocab_size = len(self.tokenizer.vocab)
tokenizer_info = xgr.TokenizerInfo( # type: ignore
encoded_vocab=self.tokenizer.vocab,
# NOTE: https://github.com/mlc-ai/xgrammar/blob/5e141f6ff1ca02bc31f9e512e68b61f2a8ae88e5/tests/python/test_tokenizer_info.py#L43 # noqa: E501
vocab_type=xgr.VocabType.RAW
if self.tokenizer.is_tekken
else xgr.VocabType.BYTE_FALLBACK,
vocab_size=self.vocab_size,
stop_token_ids=stop_token_ids,
add_prefix_space=True,
)
elif is_plamo3 and callable(
if is_plamo3 and callable(
init_xgrammar := getattr(self.tokenizer, "init_xgrammar", None)
):
tokenizer_info, _ = init_xgrammar()