[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
-11
View File
@@ -638,7 +638,6 @@ class EngineArgs:
:class:`QuantizationConfigArgs`. Auto-populated from the matching online
shorthand when `quantization` is one of the values in
`ONLINE_QUANT_SHORTHAND_NAMES`."""
allow_deprecated_quantization: bool = ModelConfig.allow_deprecated_quantization
enforce_eager: bool = ModelConfig.enforce_eager
disable_custom_all_reduce: bool = ParallelConfig.disable_custom_all_reduce
enable_shm_tensor_arena: bool = ParallelConfig.enable_shm_tensor_arena
@@ -675,7 +674,6 @@ class EngineArgs:
mm_encoder_fp8_scale_save_margin: float = (
MultiModalConfig.mm_encoder_fp8_scale_save_margin
)
io_processor_plugin: str | None = None
renderer_num_workers: int = 1
skip_mm_profiling: bool = MultiModalConfig.skip_mm_profiling
video_pruning_rate: float | None = MultiModalConfig.video_pruning_rate
@@ -981,10 +979,6 @@ class EngineArgs:
model_group.add_argument(
"--quantization-config", **model_kwargs["quantization_config"]
)
model_group.add_argument(
"--allow-deprecated-quantization",
**model_kwargs["allow_deprecated_quantization"],
)
model_group.add_argument("--enforce-eager", **model_kwargs["enforce_eager"])
model_group.add_argument(
"--enable-return-routed-experts",
@@ -1053,9 +1047,6 @@ class EngineArgs:
model_group.add_argument(
"--logits-processors", **model_kwargs["logits_processors"]
)
model_group.add_argument(
"--io-processor-plugin", **model_kwargs["io_processor_plugin"]
)
model_group.add_argument(
"--renderer-num-workers",
**model_kwargs["renderer_num_workers"],
@@ -2000,7 +1991,6 @@ class EngineArgs:
max_model_len=self.max_model_len,
quantization=self.quantization,
quantization_config=self.quantization_config,
allow_deprecated_quantization=self.allow_deprecated_quantization,
enforce_eager=self.enforce_eager,
return_sampling_mask=self.return_sampling_mask,
max_logprobs=self.max_logprobs,
@@ -2046,7 +2036,6 @@ class EngineArgs:
mm_ipc_gpu_memory_gb=self.mm_ipc_gpu_memory_gb,
mm_device_do_normalize=self.mm_device_do_normalize,
mm_processor_device=self.mm_processor_device,
io_processor_plugin=self.io_processor_plugin,
renderer_num_workers=self.renderer_num_workers,
)