The AI Toolchain — issue -432, November 28, 2019

Triton v1.8.0 adds CUDA shared memory support and string tensor handling in perf_client

$ git clone --branch v1.8.0 https://github.com/triton-inference-server/server.git
# already have the repo? check out this version:
$ git checkout v1.8.0

• ›Adds CUDA shared memory support, expanding shared-memory capabilities beyond CPU/pinned memory.
• ›Adds string tensor support to perf_client, enabling performance benchmarking of string-typed inputs and outputs.
• ›Improves perf_client command-line arguments for easier use while maintaining compatibility with existing arguments.
• ›Improves pinned-memory efficiency for ensemble models.

Milvus v0.5.3 doubles search-result transmission speed and adds new SDK APIs for id/distance retrieval across Python, Java, and C++.

$ git clone --branch v0.5.3 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:
$ git checkout v0.5.3

for id_list, dis_list in zip(results.id_array, results.distance_array):
    for id, dis in zip(id_list, dis_list):
        print("id={}, distance={}".format(id, dis))

id = results.id_array[i][j]
distance = results.distance_array[i][j]

• ›Adds results.id_array[i][j] and results.distance_array[i][j] accessors in the Python SDK to retrieve a specific target vector's id and distance from search results.
• ›Splits search result ids and distances into separate arrays (results.id_array, results.distance_array) in the Python SDK, reducing API response time and enabling faster looping when nq and topk are large.
• ›Adds getResultIdsList and getResultDistancesList methods to the Java SDK for retrieving search result ids and distances separately with better performance, alongside the existing getQueryResultsList returning QueryResult objects.
• ›Adds keepalive and idleTimeout settings in the Java SDK when connecting to the Milvus server.
• ›Doubles the transmission speed of search results to client applications via gRPC message optimizations and API changes.

$ git clone --branch v0.5.1 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:
$ git checkout v0.5.1

Weaviate 0.21.2 adds dedicated /v1/.well-known/live and /v1/.well-known/ready health endpoints that bypass auth.

$ git clone --branch 0.21.2 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout 0.21.2

$ curl -sf http://weaviate:8080/v1/.well-known/live && echo 'alive'

$ curl -sf http://weaviate:8080/v1/.well-known/ready && echo 'ready'

• ›Adds unauthenticated liveness endpoint GET /v1/.well-known/live returning 204 No Content when the Weaviate instance is alive, bypassing OIDC and other auth schemes.
• ›Adds unauthenticated readiness endpoint GET /v1/.well-known/ready returning 204 No Content when the instance is ready to serve traffic, decoupled from auth-protected endpoints like /v1/meta.

$ git clone --branch 0.21.1 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout 0.21.1

$ git clone --branch 0.21.0 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout 0.21.0

$ curl -X PATCH 'http://localhost:8080/v1/things/<id>' \
  -H 'Content-Type: application/json' \
  -d '{"class": "Article", "schema": {"title": "Updated Title"}}'

$ git clone --branch 0.20.4 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout 0.20.4