xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-28 02:18:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix Deepseek V2 fp8 kv-scale remapping (#11947)

Browse Source 
Signed-off-by: Yida Wu <yidawu@alumni.cmu.edu>
This commit is contained in:
Concurrensee 2025-01-13 01:05:06 -06:00 committed by GitHub
parent 80ea3af1a0
commit cf6bbcb493
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/models/deepseek_v2.py
View File

@ -45,7 +45,8 @@ from vllm.model_executor.layers.rotary_embedding import get_rope
from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
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
@ -635,6 +636,11 @@ class DeepseekV2ForCausalLM(nn.Module, SupportsPP):
if name.endswith(".bias") and name not in params_dict:
continue
# Remapping the name of FP8 kv-scale.
name = maybe_remap_kv_scale_name(name, params_dict)
if name is None:
continue
if is_pp_missing_parameter(name, self):
continue