Skip to content

[Feature]: PD separation supports prefix caching #12257 #1

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

Closed
wants to merge 1 commit into from
Closed

[Feature]: PD separation supports prefix caching #12257 #1

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
4 changes: 2 additions & 2 deletions vllm/distributed/kv_transfer/kv_connector/simple_connector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ def send_kv_caches_and_hidden_states(
) -> None:

input_tokens_tensor = model_input.input_tokens
seq_lens = model_input.attn_metadata.seq_lens
seq_lens = (model_input.attn_metadata.seq_lens_tensor - model_input.attn_metadata.context_lens_tensor).tolist()
slot_mapping_flat = model_input.attn_metadata.slot_mapping.flatten()
start_layer = model_executable.model.start_layer
end_layer = model_executable.model.end_layer
Expand Down Expand Up @@ -212,7 +212,7 @@ def recv_kv_caches_and_hidden_states(
bypass_model_exec = True

input_tokens_tensor = model_input.input_tokens
seq_lens = model_input.attn_metadata.seq_lens
seq_lens = (model_input.attn_metadata.seq_lens_tensor - model_input.attn_metadata.context_lens_tensor).tolist()
slot_mapping = model_input.attn_metadata.slot_mapping.flatten()

hidden_or_intermediate_states_for_one_req = []
Expand Down
Loading