sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 108 Packages Projects Releases Wiki Activity

arch: refactor LLM_TENSOR_NAMES (#18051)

Browse Source 
* arch: refactor LLM_TENSOR_NAMES

* update docs

* typo

* fix LLM_ARCH_NEMOTRON_H_MOE

* show more meaningful error message on missing tensor

* fix and tested LLM_ARCH_NEMOTRON_H_MOE
This commit is contained in:
Xuan-Son Nguyen
2025-12-16 13:22:30 +01:00
committed by GitHub
parent 7b1db3d3b7
commit 7f2b2f3c77
3 changed files with 1897 additions and 2284 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/development/HOWTO-add-model.md
+1 -1
View File
@@ -97,7 +97,7 @@ The model params and tensors layout must be defined in `llama.cpp` source files:
1. Define a new `llm_arch` enum value in `src/llama-arch.h`.
2. In `src/llama-arch.cpp`:
- Add the architecture name to the `LLM_ARCH_NAMES` map.
- Add the tensor mappings to the `LLM_TENSOR_NAMES` map.
- Add the list of model tensors to `llm_get_tensor_names` (you may also need to update `LLM_TENSOR_NAMES`)
3. Add any non-standard metadata loading in the `llama_model_loader` constructor in `src/llama-model-loader.cpp`.
4. If the model has a RoPE operation, add a case for the architecture in `llama_model_rope_type` function in `src/llama-model.cpp`.