Skip to content

LLM inference in C/C++

C++ ggml

common : move llama_n_rs_seq to before llama_decode (#28749)

Daniel Bevenius093a2f86c3e3
diff --git a/common/common.cpp b/common/common.cpp
index d162a38800..d8319cd9ac 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -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");