Skip to content

Make weight all-gathers explicit for DSv3 batch-split #3406

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
copybara-service merged 1 commit into from
Mar 17, 2026
Merged

Make weight all-gathers explicit for DSv3 batch-split #3406

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
121 changes: 121 additions & 0 deletions src/maxtext/models/deepseek_batchsplit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,6 +168,126 @@ def merge(x, split_factor=2):
return jnp.reshape(x, (-1,) + x.shape[2:])


def gather_weights(weights, mesh):
"""all-gathers FSDP sharded weights."""

def fn(weights):
(
(pre_attn_norm, post_attn_norm),
(wq_a, wq_b, q_norm, wkv_a, wkv_b, kv_norm, out),
), (
(gate, bias),
(routed_wi_0, routed_wi_1, routed_wo),
(shared_wi_0, shared_wi_1, shared_wo),
) = weights
# All-gather across FSDP axis. Expert axis is used for FSDP in attention.
wq_a = jax.lax.all_gather(wq_a, axis_name="expert", tiled=True, axis=1)
wq_a = jax.lax.all_gather(wq_a, axis_name="fsdp", tiled=True)
wq_b = jax.lax.all_gather(wq_b, axis_name="expert", tiled=True, axis=1)
wq_b = jax.lax.all_gather(wq_b, axis_name="fsdp", tiled=True)
wkv_a = jax.lax.all_gather(wkv_a, axis_name="expert", tiled=True, axis=1)
wkv_a = jax.lax.all_gather(wkv_a, axis_name="fsdp", tiled=True)
wkv_b = jax.lax.all_gather(wkv_b, axis_name="expert", tiled=True, axis=1)
wkv_b = jax.lax.all_gather(wkv_b, axis_name="fsdp", tiled=True)
out = jax.lax.all_gather(out, axis_name="expert", tiled=True)
out = jax.lax.all_gather(out, axis_name="fsdp", tiled=True, axis=2)
gate = jax.lax.all_gather(gate, axis_name="fsdp", tiled=True)
routed_wi_0 = jax.lax.all_gather(routed_wi_0, axis_name="fsdp", tiled=True)
routed_wi_1 = jax.lax.all_gather(routed_wi_1, axis_name="fsdp", tiled=True)
routed_wo = jax.lax.all_gather(routed_wo, axis_name="fsdp", tiled=True)
shared_wi_0 = jax.lax.all_gather(shared_wi_0, axis_name="expert", tiled=True, axis=1)
shared_wi_0 = jax.lax.all_gather(shared_wi_0, axis_name="fsdp", tiled=True)
shared_wi_1 = jax.lax.all_gather(shared_wi_1, axis_name="expert", tiled=True, axis=1)
shared_wi_1 = jax.lax.all_gather(shared_wi_1, axis_name="fsdp", tiled=True)
shared_wo = jax.lax.all_gather(shared_wo, axis_name="expert", tiled=True)
shared_wo = jax.lax.all_gather(shared_wo, axis_name="fsdp", tiled=True, axis=1)
return (
(
(pre_attn_norm, post_attn_norm),
(wq_a, wq_b, q_norm, wkv_a, wkv_b, kv_norm, out),
),
(
(gate, bias),
(routed_wi_0, routed_wi_1, routed_wo),
(shared_wi_0, shared_wi_1, shared_wo),
),
)

return jax.shard_map(
fn,
mesh=mesh,
in_specs=(
(
(
(
jax.sharding.PartitionSpec(None),
jax.sharding.PartitionSpec(None),
),
(
jax.sharding.PartitionSpec("fsdp", "expert"),
jax.sharding.PartitionSpec("fsdp", "expert", None),
jax.sharding.PartitionSpec(None),
jax.sharding.PartitionSpec("fsdp", "expert"),
jax.sharding.PartitionSpec("fsdp", "expert", None),
jax.sharding.PartitionSpec(None),
jax.sharding.PartitionSpec("expert", None, "fsdp"),
),
),
(
(
jax.sharding.PartitionSpec("fsdp", None),
jax.sharding.PartitionSpec(None),
),
(
jax.sharding.PartitionSpec("fsdp", None, "expert"),
jax.sharding.PartitionSpec("fsdp", None, "expert"),
jax.sharding.PartitionSpec("fsdp", "expert", None),
),
(
jax.sharding.PartitionSpec("fsdp", "expert"),
jax.sharding.PartitionSpec("fsdp", "expert"),
jax.sharding.PartitionSpec("expert", "fsdp"),
),
),
),
),
out_specs=(
(
(
jax.sharding.PartitionSpec(None),
jax.sharding.PartitionSpec(None),
),
(
jax.sharding.PartitionSpec(None, None),
jax.sharding.PartitionSpec(None, None, None),
jax.sharding.PartitionSpec(None),
jax.sharding.PartitionSpec(None, None),
jax.sharding.PartitionSpec(None, None, None),
jax.sharding.PartitionSpec(None),
jax.sharding.PartitionSpec(None, None, None),
),
),
(
(
jax.sharding.PartitionSpec(None, None),
jax.sharding.PartitionSpec(None),
),
(
jax.sharding.PartitionSpec(None, None, "expert"),
jax.sharding.PartitionSpec(None, None, "expert"),
jax.sharding.PartitionSpec(None, "expert", None),
),
(
jax.sharding.PartitionSpec(None, None),
jax.sharding.PartitionSpec(None, None),
jax.sharding.PartitionSpec(None, None),
),
),
),
check_vma=False,
)(weights)


def scan_batch_split_layers(
inputs,
params,
Expand All @@ -183,6 +303,7 @@ def scan_batch_split_layers(
"""Scans the layers with batch-split schedule."""

def batch_split_scan_fn(inputs, weights, dpos, dseg):
weights = gather_weights(weights, mesh)
xs = batch_split_schedule(
inputs,
weights,
Expand Down
Loading