Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dev-willbird1936/gguf-rwkv-trie-oob-poc# Run inference directly in the terminal:
llama cli -hf dev-willbird1936/gguf-rwkv-trie-oob-pocInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dev-willbird1936/gguf-rwkv-trie-oob-poc# Run inference directly in the terminal:
llama cli -hf dev-willbird1936/gguf-rwkv-trie-oob-pocUse pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf dev-willbird1936/gguf-rwkv-trie-oob-poc# Run inference directly in the terminal:
./llama-cli -hf dev-willbird1936/gguf-rwkv-trie-oob-pocBuild from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf dev-willbird1936/gguf-rwkv-trie-oob-poc# Run inference directly in the terminal:
./build/bin/llama-cli -hf dev-willbird1936/gguf-rwkv-trie-oob-pocUse Docker
docker model run hf.co/dev-willbird1936/gguf-rwkv-trie-oob-pocYAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
llamacpp-05 PoC: RWKV tokenizer trie-walk heap out-of-bounds read
llamacpp05_rwkv_trie_oob.gguf is a minimal GGUF file (640 bytes) that selects the RWKV tokenizer (tokenizer.ggml.model = "rwkv") and defines a 3-token vocabulary where one token's escaped text decodes to bytes containing an embedded NUL (0x00). Building the tokenizer's naive_trie from that token plants a NUL edge inside the trie.
llama_tokenize's RWKV session tokenize loop advances the scan position with a pre-increment, text[++position], with no bounds check against text.size(). When the walk reaches the input's real end, the C-string terminator at text[size()] matches the trie's NUL edge and the loop does not stop: the next pre-increment reads text[size()+1], one byte past the heap-allocated std::string buffer.
Confirmed with AddressSanitizer: heap-buffer-overflow READ of size 1 at llama-vocab.cpp:1323, reached through the real, public llama_tokenize API, no internal-only code path involved.
Load this file with any llama.cpp build (or any consumer that calls llama_tokenize on text long enough to exceed the small-string optimization threshold) to trigger the read.
- Downloads last month
- -
We're not able to determine the quantization variants.
# Gated model: Login with a HF token with gated access permission hf auth login