[V1] Make v1 more testable (#9888)

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
This commit is contained in:
Joe Runde
2024-11-06 11:57:35 -08:00
committed by GitHub
parent 87bd7e0515
commit d58268c56a
75 changed files with 243 additions and 165 deletions
+2 -2
View File
@@ -44,7 +44,7 @@ from vllm.model_executor.layers.linear import (ColumnParallelLinear,
RowParallelLinear)
from vllm.model_executor.layers.logits_processor import LogitsProcessor
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.layers.sampler import Sampler, SamplerOutput
from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
from vllm.model_executor.layers.vocab_parallel_embedding import (
DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
@@ -1141,7 +1141,7 @@ class MllamaForConditionalGeneration(nn.Module, SupportsMultiModal):
)
self.logits_processor = LogitsProcessor(config.output_hidden_states,
config.text_config.vocab_size)
self.sampler = Sampler()
self.sampler = get_sampler()
def compute_logits(
self,