Skip to content

Commit b6cd9cc

Browse files
Panxuanyuext.yanwei25
authored andcommitted
bugfix: modify parameter description for enable_prefetch_weight
1 parent 3416a45 commit b6cd9cc

File tree

1 file changed

+6
-3
lines changed

1 file changed

+6
-3
lines changed

xllm/core/common/global_flags.cpp

Lines changed: 6 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -390,6 +390,9 @@ DEFINE_string(reasoning_parser,
390390
// --- qwen3 reranker config ---
391391
DEFINE_bool(enable_qwen3_reranker, false, "Whether to enable qwen3 reranker.");
392392

393-
DEFINE_bool(enable_prefetch_weight,
394-
false,
395-
"Whether to enable prefetch weight.");
393+
DEFINE_bool(
394+
enable_prefetch_weight,
395+
false,
396+
"Whether to enable prefetch weight,only applicable to Qwen3-dense model."
397+
"The default prefetching ratio for gateup weight is 40%."
398+
"If adjustments are needed, e.g. export PREFETCH_COEFFOCIENT=0.5");

0 commit comments

Comments
 (0)