[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:
@@ -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,
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user