UPSTREAM PR #19796: Add model metadata loading from huggingface for use with tests requiring real model data

[loci-dev]

Note

Source pull request: ggml-org/llama.cpp#19796

This is based on the work from huggingface here:

https://github.com/huggingface/huggingface.js/tree/main/packages/gguf

Idea is to partially load GGUF models from huggingface, just enough to get the metadata

The intention is to use this data with realistic unit tests for llama-quant.cpp, but it can be used for anyone needing real model data

To build:

cmake --build build --target test-gguf-model-data

To run the included test:

./build/bin/test-gguf-model-data
=== test-gguf-model-data ===
gguf_fetch: loaded from cache: /home/colin/.cache/llama.cpp/gguf-headers/ggml-org_Qwen3-0.6B-GGUF--Qwen3-0.6B-Q8_0.gguf.partial
Architecture: qwen3
n_embd:       1024
n_ff:         3072
n_vocab:      151936
n_layer:      28
n_head:       16
n_head_kv:    8
n_expert:     0
n_embd_head_k:128
n_embd_head_v:128
tensors:      311
gguf_fetch: loaded from cache: /home/colin/.cache/llama.cpp/gguf-headers/ggml-org_Qwen3-0.6B-GGUF--Qwen3-0.6B-Q8_0.gguf.partial
=== ALL TESTS PASSED ===

Caches the model locally for faster subsequent usages

Unit test provided as an example for usage in future tests

AI was used to help with the porting process and writing the unit tests

[loci-review]

No meaningful performance changes were detected across 111671 analyzed functions in the following binaries: build.bin.llama-cvector-generator, build.bin.libmtmd.so, build.bin.libllama.so, build.bin.llama-tts, build.bin.llama-tokenize, build.bin.llama-bench, build.bin.llama-gguf-split, build.bin.llama-llava-cli, build.bin.llama-minicpmv-cli, build.bin.llama-quantize, build.bin.llama-qwen2vl-cli, build.bin.llama-gemma3-cli, build.bin.libggml-base.so, build.bin.libggml-cpu.so, build.bin.libggml.so.

🔎 Full breakdown: Loci Inspector.
💬 Questions? Tag @loci-dev.

[loci-review]

No meaningful performance changes were detected across 111671 analyzed functions in the following binaries: build.bin.libllama.so, build.bin.llama-tts, build.bin.llama-cvector-generator, build.bin.libmtmd.so, build.bin.llama-tokenize, build.bin.libggml-base.so, build.bin.libggml-cpu.so, build.bin.libggml.so, build.bin.llama-bench, build.bin.llama-gemma3-cli, build.bin.llama-gguf-split, build.bin.llama-llava-cli, build.bin.llama-minicpmv-cli, build.bin.llama-quantize, build.bin.llama-qwen2vl-cli.

🔎 Full breakdown: Loci Inspector
💬 Questions? Tag @loci-dev

[loci-review]

No meaningful performance changes were detected across 111671 analyzed functions in the following binaries: build.bin.libllama.so, build.bin.llama-tts, build.bin.llama-cvector-generator, build.bin.libmtmd.so, build.bin.llama-tokenize, build.bin.libggml-base.so, build.bin.libggml-cpu.so, build.bin.libggml.so, build.bin.llama-quantize, build.bin.llama-qwen2vl-cli, build.bin.llama-gemma3-cli, build.bin.llama-gguf-split, build.bin.llama-llava-cli, build.bin.llama-minicpmv-cli, build.bin.llama-bench.

🔎 Full breakdown: Loci Inspector
💬 Questions? Tag @loci-dev