Block or Report
Block or report lxning
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePopular repositories
-
-
-
multi-model-server Public
Forked from awslabs/multi-model-server
Multi Model Server is a tool for serving neural net models for inference
Java
-
server Public
Forked from triton-inference-server/server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
C++
-
deep-learning-containers Public
Forked from aws/deep-learning-containers
AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.
Python
247 contributions in the last year
Contribution activity
April 2023
Created 10 commits in 1 repository
Created a pull request in pytorch/serve that received 2 comments
TorchServe decompress tgz format model
Description Please read our CONTRIBUTING.md prior to creating your first pull request. Please include a summary of the feature or issue being fixed…
Opened 3 other pull requests in 1 repository
pytorch/serve
2
merged
1
open
Reviewed 16 pull requests in 2 repositories
pytorch/serve
15 pull requests
- update ping endpoint default behavior
- http stream response via http 1.1 chunked encoding
- open github issue on regression failure
- Frontend metrics configuration handling
- Change docker image to production
- Large model inference
- deepspeed base handler and example
- Refactor PT2 code changes
- fix core pinning enabling in cpu nightly benchmark
- fixes error thrown while loading multiple models
- Enable worker core pinning in CPU nightly benchmark
- Frontend IMetrics, LogMetric and PrometheusMetric
- feat: add PyTorch/XLA support
- Micro batching example
- [WIP] Add metric cache and migrate existing metrics to cache implementation


