You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
if model_dft is not selected, the slot.spec is not allocated, hence common_speculative_free is called with a nullptr (introduced in commit 9ca2e67)
if model_dft is not selected, slot.batch_spec is initialized as default, and llama_batch_free with the default value causes memory corruption (introduced in commit 10bce04)
suggested fix -
check for slot.spec before calling common_speculative_free
convert slot.batch_spec to pointer, check for allocation and then call llama_batch_free
Name and Version
$ ./build/bin/llama-cli --version
version: 4242 (642330a)
built with Homebrew clang version 18.1.5 for arm64-apple-darwin23.3.0
Operating systems
Linux, Mac, Windows
Which llama.cpp modules do you know to be affected?
llama-server
Problem description & steps to reproduce
in the destructor of server_context -
common_speculative_free
is called with a nullptr (introduced in commit 9ca2e67)suggested fix -
kind attn: @ggerganov @slaren
First Bad Commit
first bad commit: 9ca2e67
second bad commit: 10bce04
Relevant log output
The text was updated successfully, but these errors were encountered: