talk-llama : sync llama.cpp

ggml-ci
2026-10-21 01:31:53 +02:00 · 2025-06-18 12:40:34 +03:00
parent 69061e356f
commit 2f60ebc3c2
26 changed files with 1454 additions and 504 deletions
@@ -4,7 +4,7 @@

 #include <cstdint>

-#define LLAMA_MAX_PARALLEL_SEQUENCES 64
+#define LLAMA_MAX_SEQ 64

 struct llama_cparams {
    uint32_t n_ctx;           // context size used during inference