]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model: move `load_hparams` and `load_tensors` to per-model definition (#22004)
authorXuan-Son Nguyen <redacted>
Mon, 4 May 2026 10:36:59 +0000 (12:36 +0200)
committerGitHub <redacted>
Mon, 4 May 2026 10:36:59 +0000 (12:36 +0200)
commit994118a1831fdede28ee2d228e0570db9b728c45
treee907b3bfe32589d24e2328448be8c5fa913f94ee
parentc84e6d6db5c637ad8aacfdd41cf96fc1d2b85cec
model: move `load_hparams` and `load_tensors` to per-model definition (#22004)

* git-friendly migration

* add build_graph

* nits

* exclude old code from build

* wip

* add llm_arch_model_i

* prepare downstream functions

* nits

* nits

* wip

* wip

* add back create_tensor_qkv

* fix files missing include

* enforce one llm_build per arch

* cmake: use glob

* missing model params

* nits

* wip

* wip (2)

* wip (3)

* test-llama-archs is happy

* improve switch case

* move more stuff into llm_arch_model_i

* fix downstream code

* nits

* nits (2)

* fix order

* llama_model_base

* LLAMA_LOAD_LOCALS

* small fix

* fix build errors

* auto

* rm migration script and ifdef
138 files changed:
src/llama-model.cpp
src/llama-model.h
src/llama-quant.cpp
src/llama.cpp
src/models/afmoe.cpp
src/models/apertus.cpp
src/models/arcee.cpp
src/models/arctic.cpp
src/models/arwkv7.cpp
src/models/baichuan.cpp
src/models/bailingmoe.cpp
src/models/bailingmoe2.cpp
src/models/bert.cpp
src/models/bitnet.cpp
src/models/bloom.cpp
src/models/chameleon.cpp
src/models/chatglm.cpp
src/models/codeshell.cpp
src/models/cogvlm.cpp
src/models/cohere2-iswa.cpp [deleted file]
src/models/cohere2.cpp [new file with mode: 0644]
src/models/command-r.cpp
src/models/dbrx.cpp
src/models/deci.cpp
src/models/deepseek.cpp
src/models/deepseek2.cpp
src/models/deepseek2ocr.cpp [new file with mode: 0644]
src/models/dots1.cpp
src/models/dream.cpp
src/models/ernie4-5-moe.cpp
src/models/ernie4-5.cpp
src/models/eurobert.cpp
src/models/exaone-moe.cpp
src/models/exaone.cpp
src/models/exaone4.cpp
src/models/falcon-h1.cpp
src/models/falcon.cpp
src/models/gemma-embedding.cpp
src/models/gemma.cpp
src/models/gemma2-iswa.cpp [deleted file]
src/models/gemma2.cpp [new file with mode: 0644]
src/models/gemma3.cpp
src/models/gemma3n-iswa.cpp [deleted file]
src/models/gemma3n.cpp [new file with mode: 0644]
src/models/gemma4-iswa.cpp [deleted file]
src/models/gemma4.cpp [new file with mode: 0644]
src/models/glm-dsa.cpp [new file with mode: 0644]
src/models/glm4-moe.cpp
src/models/glm4.cpp
src/models/gpt2.cpp
src/models/gptneox.cpp
src/models/granite-hybrid.cpp
src/models/granite-moe.cpp [new file with mode: 0644]
src/models/granite.cpp
src/models/grok.cpp
src/models/grovemoe.cpp
src/models/hunyuan-dense.cpp
src/models/hunyuan-moe.cpp
src/models/hunyuan-vl.cpp [new file with mode: 0644]
src/models/internlm2.cpp
src/models/jais.cpp
src/models/jais2.cpp
src/models/jamba.cpp
src/models/jina-bert-v2.cpp [new file with mode: 0644]
src/models/jina-bert-v3.cpp [new file with mode: 0644]
src/models/kimi-linear.cpp
src/models/lfm2.cpp
src/models/lfm2moe.cpp [new file with mode: 0644]
src/models/llada-moe.cpp
src/models/llada.cpp
src/models/llama-embed.cpp [new file with mode: 0644]
src/models/llama.cpp
src/models/llama4.cpp
src/models/maincoder.cpp
src/models/mamba.cpp
src/models/mamba2.cpp [new file with mode: 0644]
src/models/mimo2-iswa.cpp [deleted file]
src/models/mimo2.cpp [new file with mode: 0644]
src/models/minicpm.cpp [new file with mode: 0644]
src/models/minicpm3.cpp
src/models/minimax-m2.cpp
src/models/mistral3.cpp
src/models/mistral4.cpp [new file with mode: 0644]
src/models/models.h
src/models/modern-bert.cpp
src/models/mpt.cpp
src/models/nemotron-h-moe.cpp [new file with mode: 0644]
src/models/nemotron-h.cpp
src/models/nemotron.cpp
src/models/neo-bert.cpp
src/models/nomic-bert-moe.cpp [new file with mode: 0644]
src/models/nomic-bert.cpp [new file with mode: 0644]
src/models/olmo.cpp
src/models/olmo2.cpp
src/models/olmoe.cpp
src/models/openai-moe-iswa.cpp [deleted file]
src/models/openai-moe.cpp [new file with mode: 0644]
src/models/openelm.cpp
src/models/orion.cpp
src/models/paddleocr.cpp
src/models/pangu-embed.cpp [new file with mode: 0644]
src/models/pangu-embedded.cpp [deleted file]
src/models/phi2.cpp
src/models/phi3.cpp
src/models/phimoe.cpp [new file with mode: 0644]
src/models/plamo.cpp
src/models/plamo2.cpp
src/models/plamo3.cpp
src/models/plm.cpp
src/models/qwen.cpp
src/models/qwen2.cpp
src/models/qwen2moe.cpp
src/models/qwen2vl.cpp
src/models/qwen3.cpp
src/models/qwen35.cpp
src/models/qwen35moe.cpp
src/models/qwen3moe.cpp
src/models/qwen3next.cpp
src/models/qwen3vl-moe.cpp [deleted file]
src/models/qwen3vl.cpp
src/models/qwen3vlmoe.cpp [new file with mode: 0644]
src/models/refact.cpp
src/models/rnd1.cpp
src/models/rwkv6.cpp
src/models/rwkv6qwen2.cpp
src/models/rwkv7.cpp
src/models/seed-oss.cpp
src/models/smallthinker.cpp
src/models/smollm3.cpp
src/models/stablelm.cpp
src/models/starcoder.cpp
src/models/starcoder2.cpp
src/models/step35-iswa.cpp [deleted file]
src/models/step35.cpp [new file with mode: 0644]
src/models/t5.cpp
src/models/t5encoder.cpp
src/models/wavtokenizer-dec.cpp
src/models/xverse.cpp