feat: add per-module automatic flash attention selection (#2132)

This commit is contained in:
leejet authored and GitHub committed 2026-10-13 22:58:45 +08:00
1 parent 60423ab5f6
commit d763dae3b8
53 files changed
+805 -125

No files matched your search

+1
View File
@@ -251,6 +251,7 @@ typedef struct {
const char* tokenizer; // tokenizer.json path or main=FILE,clip-l=FILE,clip-g=FILE assignments; required for PiD and Lens
bool sage_attn;
int conditioning_cache_size; // Maximum cached conditioning entries per context; 0 disables caching (default: 4)
const char* flash_attn_mode; // on/off/auto or module assignments (e.g. "auto,te=off"); NULL/empty honors legacy flags.
} sd_ctx_params_t;
typedef struct {