TensorRT-LLMs/tensorrt_llm/executor
Yibin Li 351808efeb
fix: Use hmac authentication for pickle encryption (#3384)
* hmac initial implementation to encrypt worker and proxy queue

Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>

* set different hmac key for each pair of server/client queue

Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>

* fix comments

Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>

* fix style

Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>

---------

Signed-off-by: Yibin Li <109242046+yibinl-nvidia@users.noreply.github.com>
2025-04-17 00:40:13 +08:00
..
__init__.py Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
executor.py Update (#2978) 2025-03-23 16:39:35 +08:00
ipc.py fix: Use hmac authentication for pickle encryption (#3384) 2025-04-17 00:40:13 +08:00
postproc_worker.py fix: Use hmac authentication for pickle encryption (#3384) 2025-04-17 00:40:13 +08:00
proxy.py fix: Proper error bubbling for PyExecutor (#3321) 2025-04-15 14:49:46 +08:00
request.py Update (#2978) 2025-03-23 16:39:35 +08:00
result.py chore: Unify Python NVTX call (#3450) 2025-04-15 23:25:36 +08:00
utils.py fix: Use hmac authentication for pickle encryption (#3384) 2025-04-17 00:40:13 +08:00
worker.py fix: Use hmac authentication for pickle encryption (#3384) 2025-04-17 00:40:13 +08:00