[Frontend][Core] Add sparse NCCL weight transfer support for in-place updates (#40096)
Signed-off-by: Siddharth Bedekar <bedeksid@gmail.com> Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
co-authored by
OpenAI Codex
parent
182c67daf1
commit
266b9d9c64
+2
-11
@@ -873,14 +873,7 @@ class LLM(BeamSearchOfflineMixin, PoolingOfflineMixin, OfflineInferenceMixin):
|
||||
)
|
||||
|
||||
def start_weight_update(self, is_checkpoint_format: bool = True) -> None:
|
||||
"""
|
||||
Start a new weight update.
|
||||
|
||||
Args:
|
||||
is_checkpoint_format: Whether incoming weights are in checkpoint
|
||||
format (need layerwise processing) or kernel format (direct
|
||||
copy).
|
||||
"""
|
||||
"""Start a new weight update."""
|
||||
self.llm_engine.collective_rpc(
|
||||
"start_weight_update",
|
||||
kwargs={"is_checkpoint_format": is_checkpoint_format},
|
||||
@@ -902,9 +895,7 @@ class LLM(BeamSearchOfflineMixin, PoolingOfflineMixin, OfflineInferenceMixin):
|
||||
)
|
||||
|
||||
def finish_weight_update(self) -> None:
|
||||
"""
|
||||
Finish the current weight update.
|
||||
"""
|
||||
"""Finish the current weight update."""
|
||||
self.llm_engine.collective_rpc("finish_weight_update")
|
||||
|
||||
def __repr__(self) -> str:
|
||||
|
||||
Reference in New Issue
Block a user