EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

llama : support T5 models with unequal number of encoder-decoder layers (#15909)

Browse Source 
* Extend the support of T5 models with different encoder-decoder layers

Signed-off-by: Jie Fu <jiefu@tencent.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/constants.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update gguf-py/gguf/gguf_writer.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-arch.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-arch.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-hparams.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Rename n_dec_layer --> dec_n_layer

Signed-off-by: Jie Fu <jiefu@tencent.com>

* Adapt to cases when dec_n_layer > n_layer

Signed-off-by: Jie Fu <jiefu@tencent.com>

---------

Signed-off-by: Jie Fu <jiefu@tencent.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Jie Fu (傅杰)
2025-09-11 02:51:51 +08:00
committed by GitHub
parent 6ab397e12b
commit 4f658855fa
7 changed files with 31 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llama-arch.cpp
View File

@@ -137,6 +137,7 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
{ LLM_KV_POOLING_TYPE, "%s.pooling_type" },
{ LLM_KV_LOGIT_SCALE, "%s.logit_scale" },
{ LLM_KV_DECODER_START_TOKEN_ID, "%s.decoder_start_token_id" },
{ LLM_KV_DECODER_BLOCK_COUNT, "%s.decoder_block_count" },
{ LLM_KV_ATTN_LOGIT_SOFTCAPPING, "%s.attn_logit_softcapping" },
{ LLM_KV_FINAL_LOGIT_SOFTCAPPING, "%s.final_logit_softcapping" },
{ LLM_KV_SWIN_NORM, "%s.swin_norm" },