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

[Bugfix] Gpt-j-6B patch kv_scale to k_scale path (#10063)

Browse Source 
Signed-off-by: Alex Rakowski <alex.rakowski@amd.com>
Signed-off-by: Alex Rakowski <182798202+arakowsk-amd@users.noreply.github.com>
This commit is contained in:
arakowsk-amd 2024-11-05 21:10:40 -08:00 committed by GitHub
parent 2bcbae704c
commit ea928f608c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -36,7 +36,8 @@ from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.sampler import Sampler, SamplerOutput
from vllm.model_executor.layers.vocab_parallel_embedding import (
ParallelLMHead, VocabParallelEmbedding)
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.model_loader.weight_utils import (
default_weight_loader, maybe_remap_kv_scale_name)
from vllm.model_executor.sampling_metadata import SamplingMetadata
from vllm.sequence import IntermediateTensors
@ -308,6 +309,9 @@ class GPTJForCausalLM(nn.Module, SupportsPP):
weight_loader(param, loaded_weight, shard_id)
break
else:
name = maybe_remap_kv_scale_name(name, params_dict)
if name is None:
continue
# Skip loading extra bias for GPTQ models.
if name.endswith(".bias") and name not in params_dict:
continue