Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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: 6 additions & 0 deletions torchtitan/models/deepseek_v3/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,8 @@
qk_rope_head_dim=64,
v_head_dim=128,
mscale=0.70,
use_flex_attn=True,
attn_mask_type="block_causal",
),
"236B": DeepSeekV3ModelArgs(
vocab_size=102400,
Expand All @@ -125,6 +127,8 @@
qk_nope_head_dim=128,
qk_rope_head_dim=64,
v_head_dim=128,
use_flex_attn=True,
attn_mask_type="block_causal",
),
"671B": DeepSeekV3ModelArgs(
vocab_size=129280,
Expand All @@ -150,6 +154,8 @@
qk_nope_head_dim=128,
qk_rope_head_dim=64,
v_head_dim=128,
use_flex_attn=True,
attn_mask_type="block_causal",
),
}

Expand Down
1 change: 1 addition & 0 deletions torchtitan/models/llama3/infra/parallelize.py
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,7 @@ def apply_tp(
# the result of max, since the absolute maximum is
# used to compute the scaling factor for quantization.
torch.ops.aten.max.default,
torch._higher_order_ops.flex_attention,
}


Expand Down
Loading