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

[V1][Spec Decoding] Use model_loader.get_model() to load models (#18273)

Browse Source 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
This commit is contained in:
Mark McLoughlin
2025-05-23 03:05:44 +01:00
committed by GitHub
parent 04eb88dc80
commit c6b636f9fb
16 changed files with 59 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/model_executor/models/llama_eagle.py
View File

@@ -130,13 +130,15 @@ class LlamaModel(nn.Module):
class EagleLlamaForCausalLM(LlamaForCausalLM):
def __init__(self, *, vllm_config: VllmConfig, start_layer_id: int = 0):
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
nn.Module.__init__(self)
self.config = vllm_config. \
speculative_config.draft_model_config.hf_config
target_layer_num = vllm_config.model_config.get_num_layers(
vllm_config.parallel_config)
self.model = LlamaModel(vllm_config=vllm_config,
prefix="model",
start_layer_id=start_layer_id)
start_layer_id=target_layer_num)
logit_scale = getattr(self.config, "logit_scale", 1.0)
self.logits_processor = LogitsProcessor(self.config.vocab_size,