public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-06 22:41:59 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-08-07 21:59:49 +03:00
parent 8770492611
commit 592feef04a
14 changed files with 137 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/models/dflash.cpp
+1 -1
View File
@@ -125,7 +125,7 @@ void llama_model_dflash::load_arch_tensors(llama_model_loader &) {
layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head}, 0);
layer.wkv = create_tensor(tn(LLM_TENSOR_ATTN_KV, "weight", i), {n_embd, n_embd_head}, 0);
layer.attn_kv_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_NORM, "weight", i), {n_embd_head}, 0);
layer.wo_a = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A, "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank * o_groups}, 0);
layer.wo_a = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A, "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank, o_groups}, TENSOR_ALLOW_RESHAPE);
layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT_B, "weight", i), {o_groups * o_lora_rank, n_embd}, 0);
layer.hc_attn_fn = create_tensor(tn(LLM_TENSOR_HC_ATTN_FN, "weight", i), {hc_dim, hc_mix_dim}, 0);
examples/talk-llama/models/models.h
+5
View File
@@ -596,6 +596,11 @@ struct llama_model_qwen3vlmoe : public llama_model_base {
};
struct llama_model_qwen3tts : public llama_model_qwen3vl {
llama_model_qwen3tts(const struct llama_model_params & params) : llama_model_qwen3vl(params) {}
};
struct llama_model_phi2 : public llama_model_base {
llama_model_phi2(const struct llama_model_params & params) : llama_model_base(params) {}
void load_arch_hparams(llama_model_loader & ml) override;
examples/talk-llama/models/qwen3tts.cpp
+3
View File
@@ -0,0 +1,3 @@
#include "models.h"
// llama_model_qwen3tts reuses llama_model_qwen3vl's hparams/tensors/graph logic
examples/talk-llama/models/qwen3vl.cpp
+24 -1
View File
@@ -16,11 +16,16 @@ void llama_model_qwen3vl::load_arch_hparams(llama_model_loader & ml) {
void llama_model_qwen3vl::load_arch_tensors(llama_model_loader &) {
LLAMA_LOAD_LOCALS;
int64_t n_vocab_out = n_vocab;
if (arch == LLM_ARCH_QWEN3TTS) {
n_vocab_out = 3072;
}
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
// output
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab_out}, TENSOR_NOT_REQUIRED);
// if output is NULL, init from the input tok embed
if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
@@ -166,6 +171,24 @@ llama_model_qwen3vl::graph::graph(const llama_model & model, const llm_graph_par
// lm_head
cur = build_lora_mm(model.output, cur, model.output_s);
int64_t n_vocab_in = model.tok_embd->ne[1];
int64_t n_vocab_out = model.output->ne[1];
if (n_vocab_in > n_vocab_out) {
// case: Qwen3TTS model with codec_head as output
GGML_ASSERT(model.output_norm);
int64_t pad = n_vocab_in - n_vocab_out;
// using this trick to get a scalar -inf tensor to pad the output
ggml_tensor * neg_inf = ggml_scale_bias(ctx0,
ggml_view_1d(ctx0, model.output_norm, 1, 0),
0.0f, -INFINITY);
neg_inf = ggml_repeat_4d(ctx0, neg_inf, pad, cur->ne[1], 1, 1);
cur = ggml_concat(ctx0, neg_inf, cur, 0); // [padded .. n_vocab_out, n_stream]
} else if (n_vocab_in < n_vocab_out) {
GGML_ABORT("invalid case");
}
cb(cur, "result_output", -1);
res->t_logits = cur;