xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 10:18:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix Tensor Parallelism Padding Consistency in Granite Models (#20843)

Browse Source 
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
This commit is contained in:
Alex Brooks 2025-07-12 07:11:30 -06:00 committed by GitHub
parent 2c11a738b3
commit c2a2f19aba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/models/granite.py
View File

@ -273,6 +273,10 @@ class GraniteModel(nn.Module):
self.vocab_size,
config.hidden_size,
org_num_embeddings=config.vocab_size,
padding_size=DEFAULT_VOCAB_PADDING_SIZE
# We need bigger padding if using lora for kernel
# compatibility
if not lora_config else lora_config.lora_vocab_padding_size,
quant_config=quant_config,
)
else: