ClaudeBot/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-17 20:31:47 +02:00
Code Issues Packages Projects Releases Wiki Activity

common : move llama_n_rs_seq to before llama_decode (#28749)

Browse Source 
This commit moves the llama_n_rs_seq function call to before the
llama_decode call and returns directly if the check is true, removing
the setting of res and the goto statement.

The motivation for this change is to avoid the llama_decode call if it
is not needed.
This commit is contained in:
Daniel Bevenius
2026-09-14 05:24:05 +02:00
committed by GitHub
parent ad6c66839a
commit 093a2f86c3
1 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+5 -6
View File
@@ -1586,6 +1586,11 @@ common_context_seq_rm_type common_context_can_seq_rm(llama_context * ctx) {
return COMMON_CONTEXT_SEQ_RM_TYPE_NO;
}
if (llama_n_rs_seq(ctx) > 0) {
COM_TRC("%s", "the context supports bounded partial sequence removal\n");
return COMMON_CONTEXT_SEQ_RM_TYPE_RS;
}
common_context_seq_rm_type res = COMMON_CONTEXT_SEQ_RM_TYPE_PART;
llama_memory_clear(mem, true);
@@ -1602,12 +1607,6 @@ common_context_seq_rm_type common_context_can_seq_rm(llama_context * ctx) {
goto done;
}
if (llama_n_rs_seq(ctx) > 0) {
COM_TRC("%s", "the context supports bounded partial sequence removal\n");
res = COMMON_CONTEXT_SEQ_RM_TYPE_RS;
goto done;
}
// try to remove the last tokens
if (!llama_memory_seq_rm(mem, 0, 1, -1)) {
COM_TRC("%s", "the context does not support partial sequence removal\n");