[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
-62
View File
@@ -8,7 +8,6 @@ from transformers import PreTrainedTokenizerBase
from vllm.entrypoints.generate.base.protocol import DeltaMessage
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
from vllm.reasoning import ReasoningParser
from vllm.utils.mistral import is_mistral_tokenizer
class StreamingReasoningReconstructor:
@@ -57,35 +56,6 @@ def run_reasoning_extraction(
return reasoning, content
def run_reasoning_extraction_mistral(
reasoning_parser: ReasoningParser,
model_output: list[int],
request: ChatCompletionRequest | None = None,
streaming: bool = False,
) -> tuple[str | None, str | None]:
assert is_mistral_tokenizer(reasoning_parser.model_tokenizer), type(
reasoning_parser.model_tokenizer
)
if streaming:
reconstructor = run_reasoning_extraction_streaming_mistral(
reasoning_parser,
model_output,
request,
)
return (
reconstructor.reasoning,
reconstructor.other_content or None,
)
else:
str_output = reasoning_parser.model_tokenizer.convert_ids_to_tokens(
model_output
)
reasoning, content = run_reasoning_extraction_nonstreaming(
reasoning_parser, str_output, request
)
return reasoning, content
def run_reasoning_extraction_nonstreaming(
reasoning_parser: ReasoningParser,
model_output: list[str],
@@ -128,35 +98,3 @@ def run_reasoning_extraction_streaming(
previous_text = current_text
previous_tokens = current_tokens
return reconstructor
def run_reasoning_extraction_streaming_mistral(
reasoning_parser: ReasoningParser,
model_deltas: list[int],
request: ChatCompletionRequest | None = None,
) -> StreamingReasoningReconstructor:
assert is_mistral_tokenizer(reasoning_parser.model_tokenizer), type(
reasoning_parser.model_tokenizer
)
request = request or ChatCompletionRequest(messages=[], model="test-model")
reconstructor = StreamingReasoningReconstructor()
previous_text = ""
previous_tokens: list[int] = []
for model_delta in model_deltas:
token_delta = [model_delta]
delta = reasoning_parser.model_tokenizer.convert_ids_to_tokens([model_delta])[0]
current_text = previous_text + delta
current_tokens = previous_tokens + token_delta
delta_message = reasoning_parser.extract_reasoning_streaming(
previous_text,
current_text,
delta,
previous_tokens,
current_tokens,
token_delta,
)
if delta_message is not None:
reconstructor.append_delta(delta_message)
previous_text = current_text
previous_tokens = current_tokens
return reconstructor