vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : refactor rope norm/neox (#7634)

Browse source 
* ggml : unify rope norm/neox (CPU)

* ggml : fix compile warning

* ggml : remove GLM rope mode

ggml-ci

* metal : better rope implementation

ggml-ci

* cuda : better rope implementation

ggml-ci

* naming : n_orig_ctx -> n_ctx_orig

ggml-ci

* dev : add reminders to update backends

ggml-ci

* vulkan : fix ggml_rope_ext() usage

* cuda : fix array size + indents

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-06-05 11:29:20 +03:00 • committed by GitHub
parent 9973e81c5c
commit 2b3389677a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 485 additions and 732 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/baby-llama/baby-llama.cpp
View file

@ -522,8 +522,8 @@ static struct ggml_tensor * forward(
// wk shape [n_embd, n_embd, 1, 1]
// Qcur shape [n_embd/n_head, n_head, N, 1]
// Kcur shape [n_embd/n_head, n_head, N, 1]
struct ggml_tensor * Qcur = ggml_rope(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wq, cur), n_embd/n_head, n_head, N), KQ_pos, n_rot, 0, 0);
struct ggml_tensor * Kcur = ggml_rope(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wk, cur), n_embd/n_head, n_head, N), KQ_pos, n_rot, 0, 0);
struct ggml_tensor * Qcur = ggml_rope(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wq, cur), n_embd/n_head, n_head, N), KQ_pos, n_rot, 0);
struct ggml_tensor * Kcur = ggml_rope(ctx0, ggml_reshape_3d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wk, cur), n_embd/n_head, n_head, N), KQ_pos, n_rot, 0);
// store key and value to memory
{
@ -759,8 +759,8 @@ static struct ggml_tensor * forward_batch(
// wk shape [n_embd, n_embd, 1, 1]
// Qcur shape [n_embd/n_head, n_head, N, n_batch]
// Kcur shape [n_embd/n_head, n_head, N, n_batch]
struct ggml_tensor * Qcur = ggml_rope(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wq, cur), n_embd/n_head, n_head, N, n_batch), KQ_pos, n_rot, 0, 0);
struct ggml_tensor * Kcur = ggml_rope(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wk, cur), n_embd/n_head, n_head, N, n_batch), KQ_pos, n_rot, 0, 0);
struct ggml_tensor * Qcur = ggml_rope(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wq, cur), n_embd/n_head, n_head, N, n_batch), KQ_pos, n_rot, 0);
struct ggml_tensor * Kcur = ggml_rope(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wk, cur), n_embd/n_head, n_head, N, n_batch), KQ_pos, n_rot, 0);
assert_shape_4d(Qcur, n_embd/n_head, n_head, N, n_batch);
assert_shape_4d(Kcur, n_embd/n_head, n_head, N, n_batch);
@ -1056,7 +1056,7 @@ static struct ggml_tensor * forward_lora(
model->layers[il].wqb,
cur)),
n_embd/n_head, n_head, N),
KQ_pos, n_rot, 0, 0);
KQ_pos, n_rot, 0);
struct ggml_tensor * Kcur = ggml_rope(ctx0,
ggml_reshape_3d(ctx0,
ggml_mul_mat(ctx0,
@ -1065,7 +1065,7 @@ static struct ggml_tensor * forward_lora(
model->layers[il].wkb,
cur)),
n_embd/n_head, n_head, N),
KQ_pos, n_rot, 0, 0);
KQ_pos, n_rot, 0);
// store key and value to memory
{

12
examples/convert-legacy-llama.py
View file

@ -176,7 +176,7 @@ class Params:
rope_scaling_type: gguf.RopeScalingType | None = None
f_rope_freq_base: float | None = None
f_rope_scale: float | None = None
n_orig_ctx: int | None = None
n_ctx_orig: int | None = None
rope_finetuned: bool | None = None
ftype: GGMLFileType | None = None
@ -226,7 +226,7 @@ class Params:
with open(config_path) as f:
config = json.load(f)
rope_scaling_type = f_rope_scale = n_orig_ctx = rope_finetuned = None
rope_scaling_type = f_rope_scale = n_ctx_orig = rope_finetuned = None
rope_scaling = config.get("rope_scaling")
if rope_scaling is not None and (typ := rope_scaling.get("type")):
@ -236,7 +236,7 @@ class Params:
rope_scaling_type = gguf.RopeScalingType.LINEAR
elif typ == "yarn":
rope_scaling_type = gguf.RopeScalingType.YARN
n_orig_ctx = rope_scaling['original_max_position_embeddings']
n_ctx_orig = rope_scaling['original_max_position_embeddings']
rope_finetuned = rope_scaling['finetuned']
else:
raise NotImplementedError(f'Unknown rope scaling type: {typ}')
@ -272,7 +272,7 @@ class Params:
f_rope_freq_base = config.get("rope_theta"),
rope_scaling_type = rope_scaling_type,
f_rope_scale = f_rope_scale,
n_orig_ctx = n_orig_ctx,
n_ctx_orig = n_ctx_orig,
rope_finetuned = rope_finetuned,
)
@ -864,8 +864,8 @@ class OutputFile:
self.gguf.add_rope_scaling_type(params.rope_scaling_type)
self.gguf.add_rope_scaling_factor(params.f_rope_scale)
if params.n_orig_ctx is not None:
self.gguf.add_rope_scaling_orig_ctx_len(params.n_orig_ctx)
if params.n_ctx_orig is not None:
self.gguf.add_rope_scaling_orig_ctx_len(params.n_ctx_orig)
if params.rope_finetuned is not None:
self.gguf.add_rope_scaling_finetuned(params.rope_finetuned)

2
examples/finetune/finetune.cpp
View file

@ -564,7 +564,7 @@ static struct ggml_tensor * llama_build_lora_finetune_graphs(
const int rope_mode = 0;
return ggml_rope_ext(ctx,
t, KQ_pos, nullptr, n_rot, rope_mode, n_ctx, 0,
t, KQ_pos, nullptr, n_rot, rope_mode, n_ctx,
rope_freq_base, rope_freq_scale, 0.0f, 1.0f, 0.0f, 0.0f
);
};

2
examples/train-text-from-scratch/train-text-from-scratch.cpp
View file

@ -302,7 +302,7 @@ static struct ggml_tensor * llama_build_train_graphs(
const int rope_mode = 0;
return ggml_rope_ext(
ctx, t, KQ_pos, nullptr, n_rot, rope_mode, n_ctx, 0, rope_freq_base, rope_freq_scale, 0.0f, 1.0f, 0.0f, 0.0f
ctx, t, KQ_pos, nullptr, n_rot, rope_mode, n_ctx, rope_freq_base, rope_freq_scale, 0.0f, 1.0f, 0.0f, 0.0f
);
};