sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-13 04:24:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

spec : drop support for incompatible vocabs

Browse Source 
[no ci]
This commit is contained in:
Georgi Gerganov
2026-05-07 09:54:09 +03:00
parent cc36b7a242
commit ab4718f199
4 changed files with 10 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tools/server/server-context.cpp
View File

@@ -910,7 +910,11 @@ private:
// try speculative decoding
if (ctx_seq_rm_type != COMMON_CONTEXT_SEQ_RM_TYPE_NO) {
slot.spec.reset(common_speculative_init(params_base.speculative, slot.ctx));
try {
slot.spec.reset(common_speculative_init(params_base.speculative, slot.ctx));
} catch (const std::exception & e) {
SRV_ERR("failed to initialize speculative decoding context: %s\n", e.what());
}
if (slot.spec) {
SLT_INF(slot, "%s", "speculative decoding context initialized\n");