remove unused forward_batch function
This commit is contained in:
xaedes
parent
3794dceb7f
commit
6e280b24dc
1 changed files with 0 additions and 290 deletions
|
|
@ -656,296 +656,6 @@ void assert_shape_4d(struct ggml_tensor * tensor, int64_t ne0, int64_t ne1, int6
|
|||
GGML_ASSERT(tensor->ne[3] == ne3);
|
||||
}
|
||||
|
||||
struct ggml_tensor * forward_batch(
|
||||
struct my_llama_model * model,
|
||||
struct my_llama_kv_cache * cache,
|
||||
struct ggml_context * ctx0,
|
||||
struct ggml_cgraph * gf,
|
||||
struct ggml_tensor * tokens_input,
|
||||
const int n_tokens,
|
||||
const int n_past,
|
||||
const int n_batch) {
|
||||
|
||||
const int N = n_tokens;
|
||||
|
||||
struct my_llama_kv_cache& kv_self = *cache;
|
||||
const auto & hparams = model->hparams;
|
||||
const int n_ctx = hparams.n_ctx;
|
||||
const int n_vocab = hparams.n_vocab;
|
||||
const int n_embd = hparams.n_embd;
|
||||
const int n_layer = hparams.n_layer;
|
||||
const int n_head = hparams.n_head;
|
||||
const int n_rot = hparams.n_rot;
|
||||
const int n_ff = get_n_ff(&hparams);
|
||||
|
||||
struct ggml_tensor * tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N*n_batch);
|
||||
memcpy(tokens->data, tokens_input->data, ggml_element_size(tokens)*N*n_batch);
|
||||
|
||||
struct ggml_tensor * kc = kv_self.k;
|
||||
struct ggml_tensor * vc = kv_self.v;
|
||||
|
||||
// inpL shape [n_embd,N*n_batch,1]
|
||||
struct ggml_tensor * inpL = ggml_get_rows(ctx0, model->tok_embeddings, tokens);
|
||||
assert_shape_2d(inpL, n_embd, N*n_batch);
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
struct ggml_tensor * inpSA = inpL;
|
||||
|
||||
struct ggml_tensor * cur;
|
||||
|
||||
// lctx.use_buf(ctx0, 0);
|
||||
|
||||
// norm
|
||||
{
|
||||
// cur shape [n_embd,N*n_batch,1,1]
|
||||
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
|
||||
// cur = attention_norm*cur
|
||||
cur = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->layers[il].attention_norm, cur),
|
||||
cur);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
}
|
||||
|
||||
// self-attention
|
||||
{
|
||||
// compute Q and K and RoPE them
|
||||
// wq shape [n_embd, n_embd, 1, 1]
|
||||
// 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_inplace(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wq, cur), n_embd/n_head, n_head, N, n_batch), n_past, n_rot, 0, n_ctx);
|
||||
struct ggml_tensor * Kcur = ggml_rope_inplace(ctx0, ggml_reshape_4d(ctx0, ggml_mul_mat(ctx0, model->layers[il].wk, cur), n_embd/n_head, n_head, N, n_batch), n_past, n_rot, 0, n_ctx);
|
||||
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);
|
||||
|
||||
// store key and value to memory
|
||||
{
|
||||
// compute the transposed [N, n_embd] V matrix
|
||||
// wv shape [n_embd, n_embd, 1, 1]
|
||||
// Vcur shape [N, n_embd, n_batch, 1]
|
||||
struct ggml_tensor * Vcur = ggml_cont(ctx0,
|
||||
ggml_permute(ctx0,
|
||||
ggml_reshape_3d(ctx0,
|
||||
ggml_mul_mat(ctx0,
|
||||
model->layers[il].wv,
|
||||
cur),
|
||||
n_embd, N, n_batch),
|
||||
1, 0, 2, 3));
|
||||
assert_shape_3d(Vcur, N, n_embd, n_batch);
|
||||
|
||||
// kv_self.k shape [n_embd * n_ctx * n_batch * n_layer]
|
||||
// kv_self.v shape [n_ctx * n_embd * n_batch * n_layer]
|
||||
// k shape [n_embd * N, n_batch] == kv_self.k[:,n_past:n_past+N,:,il]
|
||||
// v shape [N, n_embd, n_batch, 1] == kv_self.v[:,n_past:n_past+N,:,il]
|
||||
|
||||
/* {
|
||||
struct ggml_tensor * k = ggml_view_1d(ctx0, kv_self.k, N*n_embd, (ggml_element_size(kv_self.k)*n_embd)*(il*n_ctx + n_past));
|
||||
struct ggml_tensor * v = ggml_view_2d(ctx0, kv_self.v, N, n_embd,
|
||||
( n_ctx)*ggml_element_size(kv_self.v),
|
||||
(il*n_ctx)*ggml_element_size(kv_self.v)*n_embd + n_past*ggml_element_size(kv_self.v));
|
||||
|
||||
// important: storing RoPE-ed version of K in the KV cache!
|
||||
ggml_build_forward_expand(gf, ggml_cpy(ctx0, Kcur, k));
|
||||
ggml_build_forward_expand(gf, ggml_cpy(ctx0, Vcur, v));
|
||||
} //*/
|
||||
|
||||
kc = ggml_set_2d_inplace(ctx0, kc,
|
||||
ggml_reshape_2d(ctx0, Kcur, n_embd*N, n_batch),
|
||||
ggml_element_size(kc)*n_embd*n_ctx,
|
||||
(ggml_element_size(kc)*n_embd)*(il*n_batch*n_ctx + n_past));
|
||||
vc = ggml_set_2d_inplace(ctx0, vc,
|
||||
ggml_reshape_2d(ctx0, Vcur, N*n_embd, n_batch),
|
||||
ggml_element_size(vc)*n_ctx*n_embd,
|
||||
ggml_element_size(vc)*(n_past + il*n_embd*n_batch*n_ctx));
|
||||
|
||||
assert_shape_1d(kc, n_embd * n_ctx * n_batch * n_layer);
|
||||
assert_shape_1d(vc, n_embd * n_ctx * n_batch * n_layer);
|
||||
}
|
||||
|
||||
// Qcur shape [n_embd/n_head, n_head, N, n_batch]
|
||||
// Q shape [n_embd/n_head, N, n_head, n_batch]
|
||||
struct ggml_tensor * Q =
|
||||
ggml_permute(ctx0,
|
||||
Qcur,
|
||||
0, 2, 1, 3);
|
||||
assert_shape_4d(Q, n_embd/n_head, N, n_head, n_batch);
|
||||
|
||||
// kv_self.k shape [n_embd * n_ctx * n_batch * n_layer]
|
||||
// K shape [n_embd/n_head, n_past + N, n_head, n_batch]
|
||||
struct ggml_tensor * K =
|
||||
ggml_permute(ctx0,
|
||||
ggml_reshape_4d(ctx0,
|
||||
ggml_view_3d(ctx0,
|
||||
kc,
|
||||
n_embd,
|
||||
(n_past + N),
|
||||
n_batch,
|
||||
n_embd*ggml_element_size(kc),
|
||||
n_ctx*n_embd*ggml_element_size(kc),
|
||||
il*n_batch*n_ctx*n_embd*ggml_element_size(kc)),
|
||||
n_embd/n_head, n_head, n_past + N, n_batch),
|
||||
0, 2, 1, 3);
|
||||
assert_shape_4d(K, n_embd/n_head, n_past + N, n_head, n_batch);
|
||||
|
||||
// K * Q
|
||||
// KQ shape [n_past + N, N, n_head, n_batch]
|
||||
struct ggml_tensor * KQ = ggml_mul_mat(ctx0, K, Q);
|
||||
assert_shape_4d(KQ, n_past + N, N, n_head, n_batch);
|
||||
|
||||
// KQ_scaled = KQ / sqrt(n_embd/n_head)
|
||||
// KQ_scaled shape [n_past + N, N, n_head, n_batch]
|
||||
struct ggml_tensor * KQ_scaled =
|
||||
ggml_scale_inplace(ctx0,
|
||||
KQ,
|
||||
ggml_new_f32(ctx0, 1.0f/sqrtf(float(n_embd)/n_head)));
|
||||
assert_shape_4d(KQ_scaled, n_past + N, N, n_head, n_batch);
|
||||
|
||||
// KQ_masked = mask_past(KQ_scaled)
|
||||
// KQ_masked shape [n_past + N, N, n_head, n_batch]
|
||||
struct ggml_tensor * KQ_masked = ggml_diag_mask_inf_inplace(ctx0, KQ_scaled, n_past);
|
||||
assert_shape_4d(KQ_masked, n_past + N, N, n_head, n_batch);
|
||||
|
||||
// KQ = soft_max(KQ_masked)
|
||||
// KQ_soft_max shape [n_past + N, N, n_head, n_batch]
|
||||
struct ggml_tensor * KQ_soft_max = ggml_soft_max_inplace(ctx0, KQ_masked);
|
||||
assert_shape_4d(KQ_soft_max, n_past + N, N, n_head, n_batch);
|
||||
|
||||
// split cached V into n_head heads
|
||||
// kv_self.v shape [n_ctx * n_embd * n_batch * n_layer]
|
||||
// V shape [n_past + N, n_embd/n_head, n_head, n_batch] == kv_self.v[:(n_past+N),:,:,il]
|
||||
struct ggml_tensor * V =
|
||||
ggml_view_4d(ctx0, vc,
|
||||
n_past + N, n_embd/n_head, n_head, n_batch,
|
||||
ggml_element_size(vc)*n_ctx,
|
||||
ggml_element_size(vc)*n_ctx*n_embd/n_head,
|
||||
ggml_element_size(vc)*n_ctx*n_embd,
|
||||
il*n_batch*n_ctx*n_embd*ggml_element_size(vc));
|
||||
assert_shape_4d(V, n_past + N, n_embd/n_head, n_head, n_batch);
|
||||
|
||||
// KQV shape [n_embd/n_head, N, n_head, n_batch]
|
||||
struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V, KQ_soft_max);
|
||||
assert_shape_4d(KQV, n_embd/n_head, N, n_head, n_batch);
|
||||
|
||||
// KQV_merged = KQV.permute(0, 2, 1, 3)
|
||||
// KQV_merged shape [n_embd/n_head, n_head, N, n_batch]
|
||||
struct ggml_tensor * KQV_merged = ggml_permute(ctx0, KQV, 0, 2, 1, 3);
|
||||
assert_shape_4d(KQV_merged, n_embd/n_head, n_head, N, n_batch);
|
||||
// KQV_merged shape
|
||||
|
||||
// cur = KQV_merged.contiguous().view(n_embd, N)
|
||||
// cur shape [n_embd,N*n_batch,1,1]
|
||||
cur = ggml_reshape_2d(ctx0, ggml_cont(ctx0, KQV_merged), n_embd, N*n_batch);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
// cur = ggml_cpy(ctx0,
|
||||
// KQV_merged,
|
||||
// ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd, N));
|
||||
|
||||
// projection (no bias)
|
||||
// cur shape [n_embd,N*n_batch,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].wo,
|
||||
cur);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
}
|
||||
|
||||
// lctx.use_buf(ctx0, 1);
|
||||
|
||||
// inpFF shape [n_embd,N*n_batch,1,1]
|
||||
struct ggml_tensor * inpFF = ggml_add_inplace(ctx0, cur, inpSA);
|
||||
assert_shape_2d(inpFF, n_embd, N*n_batch);
|
||||
|
||||
// feed-forward network
|
||||
{
|
||||
// norm
|
||||
{
|
||||
// cur shape [n_embd,N*n_batch,1,1]
|
||||
cur = ggml_rms_norm(ctx0, inpFF, rms_norm_eps);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
|
||||
// cur = ffn_norm*cur
|
||||
// cur shape [n_embd,N*n_batch,1,1]
|
||||
cur = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->layers[il].ffn_norm, cur),
|
||||
cur);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
}
|
||||
|
||||
// tmp shape [n_ff,N*n_batch,1,1]
|
||||
struct ggml_tensor * tmp = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w3,
|
||||
cur);
|
||||
assert_shape_2d(tmp, n_ff, N*n_batch);
|
||||
|
||||
// cur shape [n_ff,N*n_batch,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w1,
|
||||
cur);
|
||||
assert_shape_2d(cur, n_ff, N*n_batch);
|
||||
|
||||
// SILU activation
|
||||
// cur shape [n_ff,N*n_batch,1,1]
|
||||
cur = ggml_silu(ctx0, cur);
|
||||
assert_shape_2d(cur, n_ff, N*n_batch);
|
||||
|
||||
// cur shape [n_ff,N*n_batch,1,1]
|
||||
cur = ggml_mul(ctx0, cur, tmp);
|
||||
assert_shape_2d(cur, n_ff, N*n_batch);
|
||||
|
||||
// cur shape [n_embd,N*n_batch,1,1]
|
||||
cur = ggml_mul_mat(ctx0,
|
||||
model->layers[il].w2,
|
||||
cur);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
}
|
||||
|
||||
// cur shape [n_embd,N*n_batch,1,1]
|
||||
cur = ggml_add_inplace(ctx0, cur, inpFF);
|
||||
assert_shape_2d(cur, n_embd, N*n_batch);
|
||||
|
||||
// input for next layer
|
||||
// inpL shape [n_embd,N*n_batch,1,1]
|
||||
inpL = cur;
|
||||
assert_shape_2d(inpL, n_embd, N*n_batch);
|
||||
}
|
||||
|
||||
// norm
|
||||
{
|
||||
|
||||
// inpL shape [n_embd,N*n_batch,1,1]
|
||||
inpL = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
|
||||
assert_shape_2d(inpL, n_embd, N*n_batch);
|
||||
|
||||
// inpL = norm*inpL
|
||||
// inpL shape [n_embd,N*n_batch,1,1]
|
||||
inpL = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model->norm, inpL),
|
||||
inpL);
|
||||
|
||||
assert_shape_2d(inpL, n_embd, N*n_batch);
|
||||
|
||||
//embeddings = inpL;
|
||||
}
|
||||
|
||||
// lm_head
|
||||
// inpL shape [n_vocab,N*n_batch,1,1]
|
||||
inpL = ggml_mul_mat(ctx0, model->output, inpL);
|
||||
assert_shape_2d(inpL, n_vocab, N*n_batch);
|
||||
|
||||
{
|
||||
// inpL shape [n_vocab,N,n_batch,1]
|
||||
inpL = ggml_reshape_3d(ctx0,
|
||||
inpL,
|
||||
n_vocab, N, n_batch);
|
||||
assert_shape_3d(inpL, n_vocab, N, n_batch);
|
||||
}
|
||||
|
||||
// run the computation
|
||||
ggml_build_forward_expand(gf, inpL);
|
||||
|
||||
return inpL;
|
||||
}
|
||||
|
||||
static size_t hash(void * p) {
|
||||
return (size_t)p % GGML_GRAPH_HASHTABLE_SIZE;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue