git/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp synced 2026-05-01 03:42:01 +02:00
Code Issues Packages Projects Releases Wiki Activity
c78fb909b2
llama.cpp/tools
History
Song Li c78fb909b2
server: fix heap-buffer-overflow from negative n_discard (CVE-2026-21869) (#22267) 
* server: clamp n_discard to non-negative at JSON parse boundary (CVE-2026-21869)

A negative n_discard from client JSON causes heap-buffer-overflow in
update_slots() context-shift loop (CWE-787, CVSS 8.8). Clamp to 0 at
ingress; n_discard=0 already triggers auto-discard (n_left/2).

Ref: GHSA-8947-pfff-2f3c

* cont : cleaner

* cont : cleanerer

* cont : cleanest

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-04-23 18:39:07 +02:00
..
batched-bench libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
cli cli : cleanup auto-completion code (#21745) 2026-04-23 15:03:28 +02:00
completion libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
cvector-generator libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
export-lora libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
fit-params fit-params : refactor + add option to output estimated memory per device (#22171) 2026-04-21 09:54:36 +03:00
gguf-split libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
imatrix libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
llama-bench fit-params : refactor + add option to output estimated memory per device (#22171) 2026-04-21 09:54:36 +03:00
mtmd mtmd: also support LLAMA_ROPE_TYPE_NONE (#22242) 2026-04-22 12:16:29 +02:00
parser libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
perplexity fit-params : refactor + add option to output estimated memory per device (#22171) 2026-04-21 09:54:36 +03:00
quantize libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
results libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
rpc rpc : add native RDMA transport for RPC backend (RoCEv2) (#20590) 2026-04-15 16:44:02 +03:00
server server: fix heap-buffer-overflow from negative n_discard (CVE-2026-21869) (#22267) 2026-04-23 18:39:07 +02:00
tokenize libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
tts libs : rename libcommon -> libllama-common (#21936) 2026-04-17 11:11:46 +03:00
CMakeLists.txt llama: end-to-end tests (#19802) 2026-03-08 12:30:21 +01:00