Skip to content
Open
Changes from 1 commit
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
2 changes: 1 addition & 1 deletion vllm_gaudi/extension/bucketing/common.py
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ def expand_to_neighbor_buckets(bs_idx, bs_range, ctx_idx, ctx_range, max_num_bat
# filter rules for buckets
# prompt
def not_over_max_model_len(bs, query, ctx):
smaller_than_limit = (query + ctx * block_size) <= max_model_len
smaller_than_limit = (query + ctx * block_size) <= max_model_len + block_size * max_num_prefill_seqs
if not smaller_than_limit:
omitted_buckets.add(
("condition: (query + ctx * block_size) <= max_model_len", "-> bs, query, ctx: ", bs, query, ctx))
Expand Down
Loading