mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 32 Packages Projects Releases Wiki Activity

model : Plamo3 support (#17304)

Browse Source 
* plamo3

* fix plamo3

* clean code

* clean up the code

* fix diff

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* add chat_template if exist

* clean up the code

* fix cpu-backend

* chore: whitespace trim fix + typo fix

* Fix: address review feedback

* restore `FREQ_BASE_SWA` constant

* Fix: address review feedback2

* Fix:typecheck

* Fix: address review feedback3

* final cleanup

---------

Co-authored-by: mmngays <146910567+mmngays@users.noreply.github.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
momonga
2025-12-29 01:28:31 +09:00
committed by GitHub
parent 07a0c4ba92
commit 9c675c7140
9 changed files with 367 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
+17
View File
@@ -42,6 +42,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_PHIMOE, "phimoe" },
{ LLM_ARCH_PLAMO, "plamo" },
{ LLM_ARCH_PLAMO2, "plamo2" },
{ LLM_ARCH_PLAMO3, "plamo3" },
{ LLM_ARCH_CODESHELL, "codeshell" },
{ LLM_ARCH_ORION, "orion" },
{ LLM_ARCH_INTERNLM2, "internlm2" },
@@ -1077,6 +1078,22 @@ static std::set<llm_tensor> llm_get_tensor_names(llm_arch arch) {
LLM_TENSOR_ATTN_POST_NORM,
LLM_TENSOR_FFN_POST_NORM,
};
case LLM_ARCH_PLAMO3:
return {
LLM_TENSOR_TOKEN_EMBD,
LLM_TENSOR_OUTPUT_NORM,
LLM_TENSOR_OUTPUT,
LLM_TENSOR_ATTN_NORM,
LLM_TENSOR_ATTN_QKV,
LLM_TENSOR_ATTN_Q_NORM,
LLM_TENSOR_ATTN_K_NORM,
LLM_TENSOR_ATTN_OUT,
LLM_TENSOR_ATTN_POST_NORM,
LLM_TENSOR_FFN_NORM,
LLM_TENSOR_FFN_POST_NORM,
LLM_TENSOR_FFN_DOWN,
LLM_TENSOR_FFN_UP,
};
case LLM_ARCH_CODESHELL:
return {
LLM_TENSOR_TOKEN_EMBD,