Commit Graph
3 Commits
Author SHA1 Message Date
0329fcdac8 gguf-py : add size guards to GGUFReader (#27188)
* gguf-py : add size guards to GGUFReader

Guard kv_count, tensor_count, string length, and array length
against crafted values that cause unbounded allocation or hangs.

Assisted-by: opencode

* gguf : validate tensor data section fits within file

When no_alloc=true, gguf_init_from_reader accepted files where the
tensor data section (computed from header claims) exceeded the remaining
file size. This allowed crafted GGUF files to pass validation while
having insufficient data, leading to OOB reads when the loader later
mapped tensor data from the file.

Assisted-by: opencode

* gguf-py : move size limits into gguf_reader.py

Per review feedback, the limits are not part of gguf.h but are
arbitrary limits defined in gguf.cpp, so define them locally in
the reader instead of exporting them from constants.

Assisted-by: opencode

* remove gguf.ccp changes

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-08-19 09:35:27 +03:00
10bf611e53 llama : check LoRA tensor data is within file bounds (#27056)
* llama : check LoRA tensor data is within file bounds

* Update src/llama-adapter.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-08-16 09:38:01 +03:00
55f453b924 wavtokenizer-dec : bound posnet/convnext block_count against n_layer_all (#26892)
* wavtokenizer-dec : bound posnet/convnext block_count against n_layer_all

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-08-12 08:06:16 +03:00