ggml : update ggml_prec specification (#26675)

* ggml : update ggml_prec specification

[no ci]

* cont : add GGML_PREC_BF16

* cont : rework API

* cont : use new API

* cont : swap arg order

* cont : support for MUL_MAT_ID

* cont : fix accidental remove of "break;"

* cont : return bools, add doc TAG_GGML_PREC, clean-up

* cont : add search tag

* cont : ws
This commit is contained in:
Georgi Gerganov
2026-09-08 09:06:24 +03:00
committed by GitHub
parent 9dcf84e5ae
commit 5a6caa05fc
10 changed files with 134 additions and 22 deletions
+1 -1
View File
@@ -7659,7 +7659,7 @@ struct test_flash_attn_ext : public test_case {
ggml_tensor * out = ggml_flash_attn_ext(ctx, q, k, v, m, 1.0f/sqrtf(hsk), max_bias, logit_softcap);
ggml_flash_attn_ext_add_sinks(out, s);
ggml_flash_attn_ext_set_n_kv_max(out, n_kv_max);
ggml_flash_attn_ext_set_prec (out, prec);
ggml_prec_set_acc(out, prec);
ggml_set_name(out, "out");
return out;