CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : remove swa_full warning (#15399)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-08-19 08:45:26 +03:00
committed by GitHub
parent f0d3c7405c
commit 9d262f4bad
1 changed files with 0 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llama-context.cpp
View File

@@ -145,11 +145,6 @@ llama_context::llama_context(
__func__, n_ctx_per_seq, hparams.n_ctx_train); __func__, n_ctx_per_seq, hparams.n_ctx_train);
} }
if (!params.swa_full && cparams.n_seq_max > 1 && hparams.is_swa_any()) {
LLAMA_LOG_WARN("%s: requested n_seq_max (%u) > 1, but swa_full is not enabled -- performance may be degraded: %s\n",
__func__, cparams.n_seq_max, "https://github.com/ggml-org/llama.cpp/pull/13845#issuecomment-2924800573");
}
if (!hparams.vocab_only) { if (!hparams.vocab_only) {
// GPU backends // GPU backends
for (auto * dev : model.devices) { for (auto * dev : model.devices) {