Merge branch 'master' into patch-1

.github/workflows/benchmark_nightly_cpu.yml

@@ -4,10 +4,13 @@ on:
   # run every day at 2:15am
   schedule:
     - cron:  '15 02 * * *'
+  pull_request:
+
 jobs:
   nightly:
+    if: ${{ (github.repository_owner == 'pytorch' && contains(github.event.pull_request.body, 'RUN_BENCHMARK')) || github.event_name  == 'schedule' }}
     runs-on: [self-hosted, cpu]
-    timeout-minutes: 1320 
+    timeout-minutes: 1320
     steps:
       - name: Clean up previous run
         run: |
@@ -34,7 +37,7 @@ jobs:
         uses: actions/upload-artifact@v2
         with:
           name: nightly cpu artifact
-          path: /tmp/ts_benchmark 
+          path: /tmp/ts_benchmark
       - name: Open issue on failure
         if: ${{ failure() && github.event_name  == 'schedule' }}
         uses: rishabhgupta/git-action-issue@v2

.github/workflows/benchmark_nightly_gpu.yml

@@ -1,13 +1,17 @@
 name: Benchmark torchserve gpu nightly
 
+
 on:
   # run every day at 2:15am
   schedule:
     - cron:  '15 02 * * *'
+  pull_request:
+
 jobs:
   nightly:
+    if: ${{ (github.repository_owner == 'pytorch' && contains(github.event.pull_request.body, 'RUN_BENCHMARK')) || github.event_name  == 'schedule' }}
     runs-on: [self-hosted, gpu]
-    timeout-minutes: 1320 
+    timeout-minutes: 1320
     steps:
       - name: Clean up previous run
         run: |
@@ -34,12 +38,12 @@ jobs:
         uses: actions/upload-artifact@v2
         with:
           name: nightly gpu artifact
-          path: /tmp/ts_benchmark 
+          path: /tmp/ts_benchmark
       - name: Open issue on failure
         if: ${{ failure() && github.event_name  == 'schedule' }}
         uses: rishabhgupta/git-action-issue@v2
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
           title: Nightly GPU benchmark failed
           body:  Commit ${{ github.sha }} daily scheduled [CI run](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}) failed, please check why
-          assignees: ''
+          assignees: ''

CONTRIBUTING.md

@@ -33,7 +33,7 @@ Your contributions will fall into two categories:
           ```
     - Run Regression test `python test/regression_tests.py`
     - For running individual test suites refer [code_coverage](docs/code_coverage.md) documentation
-    - If you are updating an existing model make sure that performance hasn't degraded by running [benchmarks](https://github.com/pytorch/serve/tree/master/benchmarks) on the master branch and your branch and verify there is no performance regression
+    - If you are updating an existing model make sure that performance hasn't degraded by typing `RUN_BENCHMARK` in your PR description which will automatically trigger our comprehensive benchmarking suite
     - Run `ts_scripts/spellcheck.sh` to fix any typos in your documentation
     - For large changes make sure to run the [automated benchmark suite](https://github.com/pytorch/serve/tree/master/test/benchmark) which will run the apache bench tests on several configurations of CUDA and EC2 instances
     - If you need more context on a particular issue, please create raise a ticket on [`TorchServe` GH repo](https://github.com/pytorch/serve/issues/new/choose) or connect to [PyTorch's slack channel](https://pytorch.slack.com/)
@@ -114,4 +114,4 @@ All of our model optimization work ranging from IPEX to TensorRT work in a simil
 
 
 ### Something more complicated
-For something more complicated please open an issue and discuss it with the core team, you can see what our general priorities are here https://github.com/pytorch/serve/projects but if you need a feature urgently we are happy to guide you so you can get it done.
+For something more complicated please open an issue and discuss it with the core team, you can see what our general priorities are here https://github.com/pytorch/serve/projects but if you need a feature urgently we are happy to guide you so you can get it done.

docs/FAQs.md

@@ -15,8 +15,8 @@ Torchserve API's are compliant with the [OpenAPI specification 3.0](https://swag
 
 ### How to use Torchserve in production?
 Depending on your use case, you will be able to deploy torchserve in production using following mechanisms.
-> Standalone deployment. Refer [TorchServe docker documentation](../docker/README.md) or [TorchServe documentation](../docs/README.md)
-> Cloud based deployment. Refer [TorchServe kubernetes documentation](../kubernetes/README.md) or [TorchServe cloudformation documentation](../cloudformation/README.md)
+> Standalone deployment. Refer [TorchServe docker documentation](https://github.com/pytorch/serve/tree/master/docker#readme) or [TorchServe documentation](https://github.com/pytorch/serve/tree/master/docs#readme)
+> Cloud based deployment. Refer [TorchServe kubernetes documentation](https://github.com/pytorch/serve/tree/master/kubernetes#readme) or [TorchServe cloudformation documentation](../cloudformation/README.md)
 
 
 ### What's difference between Torchserve and a python web app using web frameworks like Flask, Django?