biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1] Make v1 more testable (#9888)

Browse Source 
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
This commit is contained in:
Joe Runde
2024-11-06 12:57:35 -07:00
committed by GitHub
parent 87bd7e0515
commit d58268c56a
75 changed files with 243 additions and 165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/models/gemma2.py
View File

@@ -33,7 +33,7 @@ from vllm.model_executor.layers.logits_processor import LogitsProcessor
from vllm.model_executor.layers.pooler import Pooler, PoolingType
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.layers.rotary_embedding import get_rope
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 (
VocabParallelEmbedding)
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
@@ -414,7 +414,7 @@ class Gemma2ForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
self.model = Gemma2Model(config, cache_config, quant_config)
self.logits_processor = LogitsProcessor(
config.vocab_size, soft_cap=config.final_logit_softcapping)
self.sampler = Sampler()
self.sampler = get_sampler()
self.make_empty_intermediate_tensors = (
self.model.make_empty_intermediate_tensors)