Skip to content

[Bugfix] Fix ColumnParallelLinearWithLoRA slice #11708

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Jan 3, 2025
Merged

[Bugfix] Fix ColumnParallelLinearWithLoRA slice #11708

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
a28ad6c
[Bugfix] Check chain_speculative_sampling before calling it (#11673)
houseroad Jan 3, 2025
5f247fc
fix wrong reference in lora/layers
zinccat Jan 3, 2025
30f12a6
Update vllm/model_executor/layers/rejection_sampler.py
jeejeelee Jan 3, 2025
a292886
[Bugfix] Check chain_speculative_sampling before calling it (#11673)
houseroad Jan 3, 2025
24c0af9
[perf-benchmark] Fix dependency for steps in benchmark pipeline (#11710)
khluu Jan 3, 2025
33d9fbc
[Model] Whisper model implementation (#11280)
aurickq Jan 3, 2025
8bcc759
[V1] Simplify Shutdown (#11659)
robertgshaw2-redhat Jan 3, 2025
aee122b
Merge branch 'vllm-project:main' into main
zinccat Jan 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions vllm/lora/layers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -479,7 +479,7 @@ def slice_lora_b(self, lora_b: torch.Tensor) -> torch.Tensor:
# ColumnParallelLinear.
else:
tensor_model_parallel_rank = get_tensor_model_parallel_rank()
shard_size = self.output_dim
shard_size = self.output_size
start_idx = tensor_model_parallel_rank * shard_size
end_idx = (tensor_model_parallel_rank + 1) * shard_size
lora_b = lora_b[:, start_idx:end_idx]
Expand All @@ -490,7 +490,7 @@ def slice_bias(self, bias: torch.Tensor) -> torch.Tensor:
if bias is None:
return bias
tensor_model_parallel_rank = get_tensor_model_parallel_rank()
shard_size = self.output_dim
shard_size = self.output_size
start_idx = tensor_model_parallel_rank * shard_size
end_idx = (tensor_model_parallel_rank + 1) * shard_size
bias = bias[start_idx:end_idx]
Expand Down
Loading