CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix SWA condition for full context reprocess (#14163)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-13 11:18:25 +03:00
committed by GitHub
parent 0889eba570
commit ffad043973
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server.cpp
View File

@@ -3217,7 +3217,7 @@ struct server_context {
} }
const auto n_swa = llama_model_n_swa(model); const auto n_swa = llama_model_n_swa(model);
if (pos_min > slot.n_past - n_swa) { if (pos_min > std::max(0, slot.n_past - n_swa)) {
SLT_WRN(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d, n_swa = %d\n", slot.n_past, (int) slot.cache_tokens.size(), slot.id, pos_min, n_swa); SLT_WRN(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d, n_swa = %d\n", slot.n_past, (int) slot.cache_tokens.size(), slot.id, pos_min, n_swa);
SLT_WRN(slot, "forcing full prompt re-processing due to lack of cache data (likely due to SWA, see %s)\n", SLT_WRN(slot, "forcing full prompt re-processing due to lack of cache data (likely due to SWA, see %s)\n",
"https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055"); "https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055");