[V1] V1 Enablement Oracle (#13726)

Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Robert Shaw
2025-03-15 01:02:20 -04:00
committed by GitHub
parent 8c0d15d5c5
commit d4d93db2c5
96 changed files with 1537 additions and 512 deletions

View File

@@ -3,10 +3,11 @@
from vllm.config import VllmConfig
from vllm.model_executor.models.llama import LlamaForCausalLM
from .interfaces import SupportsV0Only
from .utils import PPMissingLayer
class GlmForCausalLM(LlamaForCausalLM):
class GlmForCausalLM(LlamaForCausalLM, SupportsV0Only):
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
super().__init__(vllm_config=vllm_config, prefix=prefix)