sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-12 03:54:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

cont : pass seq_id

Browse Source 
[no ci]
This commit is contained in:
Georgi Gerganov
2026-05-07 10:14:18 +03:00
parent 2e389e1df9
commit ab8875567c
4 changed files with 18 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server-context.cpp
View File

@@ -912,7 +912,7 @@ private:
// try speculative decoding
if (ctx_seq_rm_type != COMMON_CONTEXT_SEQ_RM_TYPE_NO) {
try {
slot.spec.reset(common_speculative_init(params_base.speculative));
slot.spec.reset(common_speculative_init(params_base.speculative, slot.id));
} catch (const std::exception & e) {
SRV_ERR("failed to initialize speculative decoding context: %s\n", e.what());
}