[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:
@@ -70,6 +70,10 @@ logger = init_logger(__name__)
|
||||
|
||||
_TEXT_GENERATION_MODELS = {
|
||||
"Qwen3NextForCausalLM": ("qwen3_next", "Qwen3NextForCausalLM"),
|
||||
"Qwen4ExpForCausalLM": (
|
||||
"vllm.models.qwen4_exp",
|
||||
"Qwen4ExpForCausalLM",
|
||||
),
|
||||
"Qwen2ForCausalLM": ("qwen2", "Qwen2ForCausalLM"),
|
||||
"Qwen2MoeForCausalLM": ("qwen2_moe", "Qwen2MoeForCausalLM"),
|
||||
"Qwen3ForCausalLM": ("qwen3", "Qwen3ForCausalLM"),
|
||||
@@ -105,12 +109,17 @@ _MULTIMODAL_MODELS = {
|
||||
"qwen3_5",
|
||||
"Qwen3_5MoeForConditionalGeneration",
|
||||
),
|
||||
"Qwen4ExpForConditionalGeneration": (
|
||||
"vllm.models.qwen4_exp",
|
||||
"Qwen4ExpForConditionalGeneration",
|
||||
),
|
||||
}
|
||||
|
||||
_SPECULATIVE_DECODING_MODELS = {
|
||||
"DFlashDraftModel": ("qwen3_dflash", "DFlashQwen3ForCausalLM"),
|
||||
"MuseGlimmerAssistantModel": ("qwen3_dflash", "DFlashQwen3ForCausalLM"),
|
||||
"DFlashMuseGlimmerAssistantModel": ("qwen3_dflash", "DFlashQwen3ForCausalLM"),
|
||||
"Qwen4ExpMTP": ("vllm.models.qwen4_exp", "Qwen4ExpMTP"),
|
||||
"Qwen3_5MTP": ("qwen3_5_mtp", "Qwen3_5MTP"),
|
||||
"Qwen3_5MoeMTP": ("qwen3_5_mtp", "Qwen3_5MoeMTP"),
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user