CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

context : fix SWA-related warning for multiple sequences (#14045)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-06-06 13:29:18 +03:00
committed by GitHub
parent d17a809ef0
commit 487a5e0401
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-context.cpp
View File

@@ -123,7 +123,7 @@ 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) { 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", 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"); __func__, cparams.n_seq_max, "https://github.com/ggml-org/llama.cpp/pull/13845#issuecomment-2924800573");
} }