MOVZXandHinata
5aa2ac64f8
Production runs one static model behind the OpenAI-compatible API. Every adapter path and non-OpenAI HTTP surface is unreachable there. - Delete the LoRA stack: vllm/lora, LoRARequest on the engine wire, the scheduler, worker, cudagraph and MoE plumbing, LoRA metrics, the lora CLI group, and the LoRA tests. - Drop the plugin loader in vllm/plugins. Platform resolution is now CUDA-only and the general/stat-logger plugin hooks are gone. - Delete the speech-to-text and realtime entrypoints, the scale-out render routes, and vllm/config/speech_to_text.py. GenerationTask is generate-only. - Cut DecodeBenchConnector and the disagg-prefill doc and image. The Multi, Offloading and Example connectors stay; production uses the CPU KV offload tier. - Delete the ROCm-only fused KDA chunk kernel (2346 lines) with its CMake arch gate, declarations and op registrations. The CUDA build never defined the guard and no Python caller existed. - Delete the orphan Mistral and Pixtral chat fixtures and examples/. - Fix _check_model: removing the LoRA early return made every request fail with "The model ... does not exist. Valid aliases: ...". Verified on an RTX 3090: import sweep reports 1242 modules with 7 known optional-dependency failures; a live server answers chat, completions, responses, tokenize and detokenize with zero log errors and 404 for the removed surfaces; collection yields 8558 tests with the 3 pre-existing errors; ruff adds no new finding; the incremental _C build succeeds. Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
78 lines
2.7 KiB
Python
78 lines
2.7 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from unittest.mock import Mock, patch
|
|
|
|
|
|
def test_qwen3_5_lm_head_receives_quant_config():
|
|
from vllm.model_executor.models.qwen3_5 import Qwen3_5ForCausalLMBase
|
|
|
|
mock_quant_config = Mock()
|
|
|
|
mock_hf_config = Mock()
|
|
mock_hf_config.tie_word_embeddings = False
|
|
mock_hf_config.vocab_size = 128
|
|
mock_hf_config.hidden_size = 64
|
|
|
|
mock_vllm_config = Mock()
|
|
mock_vllm_config.model_config.hf_text_config = mock_hf_config
|
|
mock_vllm_config.cache_config.mamba_cache_mode = "align"
|
|
mock_vllm_config.scheduler_config = Mock()
|
|
mock_vllm_config.quant_config = mock_quant_config
|
|
|
|
mock_pp_group = Mock()
|
|
mock_pp_group.is_last_rank = True
|
|
|
|
with (
|
|
patch("vllm.model_executor.models.qwen3_5.Qwen3_5Model") as MockModel,
|
|
patch("vllm.model_executor.models.qwen3_5.ParallelLMHead") as MockLMHead,
|
|
patch("vllm.model_executor.models.qwen3_5.LogitsProcessor"),
|
|
patch(
|
|
"vllm.model_executor.models.qwen3_5.get_pp_group",
|
|
return_value=mock_pp_group,
|
|
),
|
|
):
|
|
MockModel.return_value.make_empty_intermediate_tensors = Mock()
|
|
|
|
Qwen3_5ForCausalLMBase(vllm_config=mock_vllm_config)
|
|
|
|
MockLMHead.assert_called_once()
|
|
call_kwargs = MockLMHead.call_args.kwargs
|
|
assert call_kwargs["quant_config"] is mock_quant_config
|
|
|
|
|
|
def test_qwen3_5_mtp_lm_head_receives_quant_config():
|
|
from vllm.config import CompilationMode
|
|
from vllm.model_executor.models.qwen3_5_mtp import Qwen3_5MTP
|
|
|
|
mock_quant_config = Mock()
|
|
|
|
mock_hf_config = Mock()
|
|
mock_hf_config.tie_word_embeddings = False
|
|
mock_hf_config.vocab_size = 128
|
|
mock_hf_config.hidden_size = 64
|
|
|
|
mock_vllm_config = Mock()
|
|
mock_vllm_config.model_config.hf_text_config = mock_hf_config
|
|
mock_vllm_config.cache_config.mamba_cache_mode = "align"
|
|
mock_vllm_config.compilation_config.mode = CompilationMode.NONE
|
|
mock_vllm_config.quant_config = mock_quant_config
|
|
|
|
mock_pp_group = Mock()
|
|
mock_pp_group.is_last_rank = True
|
|
|
|
with (
|
|
patch("vllm.model_executor.models.qwen3_5_mtp.Qwen3_5MultiTokenPredictor"),
|
|
patch("vllm.model_executor.models.qwen3_5_mtp.ParallelLMHead") as MockLMHead,
|
|
patch("vllm.model_executor.models.qwen3_5_mtp.LogitsProcessor"),
|
|
patch(
|
|
"vllm.model_executor.models.qwen3_5_mtp.get_pp_group",
|
|
return_value=mock_pp_group,
|
|
),
|
|
):
|
|
Qwen3_5MTP(vllm_config=mock_vllm_config)
|
|
|
|
MockLMHead.assert_called_once()
|
|
call_kwargs = MockLMHead.call_args.kwargs
|
|
assert call_kwargs["quant_config"] is mock_quant_config
|