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

[Bugfix] Fix incorrect vocal embedding shards for GGUF model in tensor parallelism (#7954)

Browse Source
This commit is contained in:
Isotr0py 2024-08-30 03:54:49 +08:00 committed by GitHub
parent c334b1898b
commit d78789ac16
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/layers/vocab_parallel_embedding.py
View File

@ -351,7 +351,10 @@ class VocabParallelEmbedding(torch.nn.Module):
param.weight_type = loaded_weight.item() param.weight_type = loaded_weight.item()
return return
elif isinstance(param, UninitializedParameter): elif isinstance(param, UninitializedParameter):
param.materialize(loaded_weight.shape, dtype=loaded_weight.dtype) shape = list(loaded_weight.shape)
if output_dim is not None:
shape[output_dim] = shape[output_dim] // self.tp_size
param.materialize(tuple(shape), dtype=loaded_weight.dtype)
# If parameter does not have output dim, then it should # If parameter does not have output dim, then it should
# be copied onto all gpus (e.g. g_idx for act_order gptq). # be copied onto all gpus (e.g. g_idx for act_order gptq).