llama : add phi3 128K model support (#7225)

* add phi3 128k support in convert-hf-to-gguf

* add phi3 128k support in cuda

* address build warnings on llama.cpp

* adjust index value in cuda long rope freq factors

* add long rope support in ggml cpu backend

* make freq factors only depend on ctx size

* remove unused rope scaling type 'su' frin gguf converter

* fix flint warnings on convert-hf-to-gguf.py

* set to the short freq factor when context size is small than trained context size

* add one line of comments

* metal : support rope freq_factors

* ggml : update ggml_rope_ext API to support freq. factors

* backends : add dev messages to support rope freq. factors

* minor : style

* tests : update to use new rope API

* backends : fix pragma semicolons

* minor : cleanup

* llama : move rope factors from KV header to tensors

* llama : remove tmp assert

* cuda : fix compile warning

* convert : read/write n_head_kv

* llama : fix uninitialized tensors

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

1 files changed, 8 insertions, 8 deletions

diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index c74e253d..1493a7ca 100644
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -1763,14 +1763,14 @@ struct test_llama : public test_llm {
                 struct ggml_tensor * Kcur = ggml_mul_mat(ctx, wk, cur);
                 struct ggml_tensor * Vcur = ggml_mul_mat(ctx, wv, cur);
 
-                Qcur = ggml_rope_custom(
-                    ctx, ggml_reshape_3d(ctx, Qcur, hp.n_embd_head, hp.n_head,    hp.n_tokens), inp_pos,
+                Qcur = ggml_rope_ext(
+                    ctx, ggml_reshape_3d(ctx, Qcur, hp.n_embd_head, hp.n_head,    hp.n_tokens), inp_pos, nullptr,
                     hp.n_rot, 0, 0, hp.n_orig_ctx, freq_base, freq_scale,
                     ext_factor, attn_factor, beta_fast, beta_slow
                 );
 
-                Kcur = ggml_rope_custom(
-                    ctx, ggml_reshape_3d(ctx, Kcur, hp.n_embd_head, hp.n_head_kv, hp.n_tokens), inp_pos,
+                Kcur = ggml_rope_ext(
+                    ctx, ggml_reshape_3d(ctx, Kcur, hp.n_embd_head, hp.n_head_kv, hp.n_tokens), inp_pos, nullptr,
                     hp.n_rot, 0, 0, hp.n_orig_ctx, freq_base, freq_scale,
                     ext_factor, attn_factor, beta_fast, beta_slow
                 );
@@ -1889,13 +1889,13 @@ struct test_falcon : public test_llm {
                 Kcur = ggml_reshape_3d(ctx, Kcur, hp.n_embd_head, hp.n_head_kv, hp.n_tokens);
 
                 // using mode = 2 for neox mode
-                Qcur = ggml_rope_custom(
-                    ctx, Qcur, inp_pos, hp.n_rot, 2, 0, hp.n_orig_ctx,
+                Qcur = ggml_rope_ext(
+                    ctx, Qcur, inp_pos, nullptr, hp.n_rot, 2, 0, hp.n_orig_ctx,
                     freq_base, freq_scale, ext_factor, attn_factor, beta_fast, beta_slow
                 );
 
-                Kcur = ggml_rope_custom(
-                    ctx, Kcur, inp_pos, hp.n_rot, 2, 0, hp.n_orig_ctx,
+                Kcur = ggml_rope_ext(
+                    ctx, Kcur, inp_pos, nullptr, hp.n_rot, 2, 0, hp.n_orig_ctx,
                     freq_base, freq_scale, ext_factor, attn_factor, beta_fast, beta_slow
                 );