Francesco Petrini

Placeholder PR to use for CI testing of https://github.com/triton-inference-server/python_backend/pull/178

Extend Logging to the python backend

1

Triton server logging functionality can now be invoked from python models. Here are a few example formats: ```python logger = pb_utils.Logger logger.log("Specific Msg!", logger.INFO) logger.log_info("Info Msg!") logger.log_warn("Warning Msg!") logger.log_error("Error Msg!")...

New Kafka Endpoint

5

Changes are made in conjunction with changes made to the third_party repo: https://github.com/triton-inference-server/third_party/pull/21

**Goal:** Support CPU shared memory between the server and client for Windows Server changes: https://github.com/triton-inference-server/server/pull/7048

**Goal:** The python client was not properly deallocating dynamic memory when destroying shared memory regions. This PR bundle fixes the leak and adds an additional test case. **Sub-Goal:** Fix the...

**Goal:** Support CPU shared memory between the server and client for Windows **Sub-goals:** Modify L0_shared_memory to run on bare-metal Windows using only Python. Client changes: https://github.com/triton-inference-server/client/pull/551 Some things to note:...

**Goal:** Provide a PR to be used as a basis for review comments. This PR adds build functionality/testing to fix arbitrary file uploads via the model load API for the...

**Goal:** Create a PR that contains the minimum number of changes necessary to validate the PA migration.