Skip to content

GitLab

Unverified Commit 959d1ab8 authored by Jimmy's avatar Jimmy Committed by GitHub
Browse files

fix(metrics): double times add_latency for DECODE_BOOTSTRAP (#12209)

parent 6c1c1933
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 1 deletion
python/sglang/srt/disaggregation/decode.py
View file @ 959d1ab8
...@@ -521,7 +521,6 @@ class DecodePreallocQueue: ...@@ -521,7 +521,6 @@ class DecodePreallocQueue:
decode_req.kv_receiver.init( decode_req.kv_receiver.init(
page_indices, decode_req.metadata_buffer_index, state_indices page_indices, decode_req.metadata_buffer_index, state_indices
) )
decode_req.req.add_latency(RequestStage.DECODE_BOOTSTRAP)
preallocated_reqs.append(decode_req) preallocated_reqs.append(decode_req)
indices_to_remove.add(i) indices_to_remove.add(i)
decode_req.req.time_stats.decode_transfer_queue_entry_time = ( decode_req.req.time_stats.decode_transfer_queue_entry_time = (
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment