Skip to content
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

[Model] Support Mistral-Nemo #6548

Merged
merged 2 commits into from
Jul 18, 2024
Merged

[Model] Support Mistral-Nemo #6548

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ef3b5ba
Support Mistral-Nemo
mgoin Jul 18, 2024
6df39b3
Merge branch 'upstream-main' into mistral-nemo-support
mgoin Jul 18, 2024
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
6 changes: 5 additions & 1 deletion vllm/model_executor/models/llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,7 @@ class LlamaAttention(nn.Module):

def __init__(
self,
config: LlamaConfig,
hidden_size: int,
num_heads: int,
num_kv_heads: int,
Expand All @@ -115,7 +116,9 @@ def __init__(
# the KV heads across multiple tensor parallel GPUs.
assert tp_size % self.total_num_kv_heads == 0
self.num_kv_heads = max(1, self.total_num_kv_heads // tp_size)
self.head_dim = hidden_size // self.total_num_heads
# MistralConfig has an optional head_dim introduced by Mistral-Nemo
self.head_dim = getattr(config, "head_dim",
self.hidden_size // self.total_num_heads)
self.q_size = self.num_heads * self.head_dim
self.kv_size = self.num_kv_heads * self.head_dim
self.scaling = self.head_dim**-0.5
Expand Down Expand Up @@ -189,6 +192,7 @@ def __init__(
attention_bias = getattr(config, "attention_bias", False) or getattr(
config, "bias", False)
self.self_attn = LlamaAttention(
config=config,
hidden_size=self.hidden_size,
num_heads=config.num_attention_heads,
num_kv_heads=getattr(config, "num_key_value_heads",
Expand Down
Loading