Merge branch 'main' into npetrovic/tilize-sweeps-new

tenstorrent · Dec 10, 2024 · 98f3d94 · 98f3d94
2 parents b7b6818 + 4bcc79b
commit 98f3d94
Show file tree

Hide file tree

Showing 299 changed files with 8,055 additions and 4,896 deletions.
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -13,4 +13,5 @@ Summarize the changes made and its impact.
 - [ ] Blackhole Post commit (if applicable)
 - [ ] Model regression CI testing passes (if applicable)
 - [ ] Device performance regression CI testing passes (if applicable)
+- [ ] **(For models and ops writers)** Full [new models](https://github.com/tenstorrent/tt-metal/actions/workflows/full-new-models-suite.yaml) tests passes
 - [ ] New/Existing tests provide coverage for changes
diff --git a/.github/workflows/_produce-data.yaml b/.github/workflows/_produce-data.yaml
@@ -22,7 +22,9 @@ on:
       - "(Single-card) Model perf tests"
       - "(Single-card) Device perf tests"
       - "(Single-card) Demo tests"
+      - "(Single-card) Tests for new models"
       - "Nightly fast dispatch tests"
+      - "(Single-card) Tests for new models"
       - "(T3K) T3000 demo tests"
       - "(T3K) T3000 model perf tests"
       - "(T3K) T3000 perplexity tests"
@@ -39,6 +41,7 @@ on:
       - "(TGG) TGG frequent tests"
       - "ttnn - Run sweeps"
       - "Blackhole post-commit tests"
+      - "Custom test dispatch"
     types:
       - completed
 

diff --git a/.github/workflows/all-post-commit-workflows.yaml b/.github/workflows/all-post-commit-workflows.yaml
@@ -2,6 +2,11 @@ name: "All post-commit tests"
 
 on:
   workflow_call:
+    inputs:
+      build-type:
+        required: false
+        default: Release
+        type: string
   workflow_dispatch:
     inputs:
       build-type:

diff --git a/.github/workflows/fast-dispatch-full-regressions-and-models-impl.yaml b/.github/workflows/fast-dispatch-full-regressions-and-models-impl.yaml
@@ -149,8 +149,8 @@ jobs:
       fail-fast: false
       matrix:
         test-config:
-          - model: "wh_b0_unstable"
-            cmd: ./tests/scripts/single_card/nightly/run_wh_b0_unstable.sh
+          - model: "stable_diffusion"
+            cmd: pytest --timeout 900 -n auto tests/nightly/single_card/stable_diffusion
           - model: "mamba 1"
             cmd: pytest --timeout 900 -n auto tests/nightly/single_card/mamba --splits 6 --group 1
           - model: "mamba 2"

diff --git a/.github/workflows/full-new-models-suite.yaml b/.github/workflows/full-new-models-suite.yaml
@@ -0,0 +1,60 @@
+name: "(Single-card) Tests for new models"
+
+on:
+  workflow_dispatch:
+    inputs:
+      build-type:
+        required: false
+        default: Release
+        type: choice
+        options:
+          - Release
+          - Debug
+          - RelWithDebInfo
+          - CI
+
+permissions:
+  actions: read
+  contents: write
+  pull-requests: write
+  pages: write
+  id-token: write
+  packages: write
+
+jobs:
+  build-docker-image-2004:
+    uses: ./.github/workflows/build-docker-artifact.yaml
+    secrets: inherit
+    with:
+      os: ubuntu-20.04-amd64
+  build-artifact:
+    needs: build-docker-image-2004
+    uses: ./.github/workflows/build-artifact.yaml
+    secrets: inherit
+    with:
+      build-docker: false
+      build-type: ${{ inputs.build-type || 'Release' }}
+  build-artifact-profiler:
+    needs: build-docker-image-2004
+    uses: ./.github/workflows/build-artifact.yaml
+    with:
+      tracy: true
+      build-docker: false
+      build-type: ${{ inputs.build-type || 'Release' }}
+    secrets: inherit
+  device-perf-single-card:
+    needs: build-artifact-profiler
+    uses: ./.github/workflows/perf-device-models-impl.yaml
+    secrets: inherit
+  e2e-model-perf-single-card:
+    needs: build-artifact
+    uses: ./.github/workflows/perf-models-impl.yaml
+    secrets: inherit
+  nightly-single-card:
+    needs: build-artifact
+    uses: ./.github/workflows/fast-dispatch-full-regressions-and-models-impl.yaml
+    secrets: inherit
+  demos-single-card:
+    needs: build-artifact
+    uses: ./.github/workflows/single-card-demo-tests-impl.yaml
+    secrets: inherit
diff --git a/.github/workflows/t3000-demo-tests-impl.yaml b/.github/workflows/t3000-demo-tests-impl.yaml
@@ -16,7 +16,7 @@ jobs:
         test-group: [
           { name: "t3k_falcon40b_tests", arch: wormhole_b0, cmd: run_t3000_falcon40b_tests, timeout: 50, owner_id: U053W15B6JF}, #Djordje Ivanovic
           { name: "t3k_llama3_tests", arch: wormhole_b0, cmd: run_t3000_llama3_tests, timeout: 30, owner_id: U03PUAKE719}, # Miguel Tairum
-          # { name: "t3k_llama3_vision_tests", arch: wormhole_b0, cmd: run_t3000_llama3_vision_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
+          { name: "t3k_llama3_vision_tests", arch: wormhole_b0, cmd: run_t3000_llama3_vision_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
           { name: "t3k_llama3_70b_tests", arch: wormhole_b0, cmd: run_t3000_llama3_70b_tests, timeout: 30, owner_id: U03FJB5TM5Y}, #Colman Glagovich
           { name: "t3k_falcon7b_tests", arch: wormhole_b0, cmd: run_t3000_falcon7b_tests, timeout: 90, owner_id: U05RWH3QUPM}, #Salar Hosseini
           { name: "t3k_mixtral_tests", arch: wormhole_b0, cmd: run_t3000_mixtral_tests, timeout: 50, owner_id: U03PUAKE719}, # Miguel Tairum

diff --git a/.github/workflows/t3000-frequent-tests-impl.yaml b/.github/workflows/t3000-frequent-tests-impl.yaml
@@ -18,9 +18,10 @@ jobs:
           { name: "t3k ethernet tests", arch: wormhole_b0, cmd: run_t3000_ethernet_tests, timeout: 60, owner_id: ULMEPM2MA}, #Sean Nijjar
           { name: "t3k trace stress tests", arch: wormhole_b0, cmd: run_t3000_trace_stress_tests, timeout: 120, owner_id: U03NG0A5ND7}, #Aditya Saigal
           { name: "t3k falcon40b tests", arch: wormhole_b0, cmd: run_t3000_falcon40b_tests, timeout: 120, owner_id: U04S2UV6L8N}, #Sofija Jovic
-          # { name: "t3k llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
-          # { name: "t3k n300 mesh llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
+          { name: "t3k llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
+          { name: "t3k n300 mesh llama3.2-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_freq_tests, timeout: 60, owner_id: U03FJB5TM5Y}, #Colman Glagovich
           { name: "t3k llama3 tests", arch: wormhole_b0, cmd: run_t3000_llama3_tests, timeout: 45, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
+          { name: "t3k llama3 accuracy tests", arch: wormhole_b0, cmd: run_t3000_llama3_accuracy_tests, timeout: 45, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
           { name: "t3k llama2_70b tests", arch: wormhole_b0, cmd: run_t3000_llama2_70b_tests, timeout: 45, owner_id: U03FJB5TM5Y}, #Colman Glagovich
           # { name: "t3k llama3_70b tests", arch: wormhole_b0, cmd: run_t3000_llama3_70b_tests, timeout: 45, owner_id: U03FJB5TM5Y}, #Colman Glagovich  # FIXME issue #14934
           { name: "t3k mixtral tests", arch: wormhole_b0, cmd: run_t3000_mixtral_tests, timeout: 60, owner_id: U03PUAKE719}, #Miguel Tairum Cruz

diff --git a/.github/workflows/t3000-unit-tests-impl.yaml b/.github/workflows/t3000-unit-tests-impl.yaml
@@ -20,8 +20,8 @@ jobs:
           { name: "t3k falcon40b tests", arch: wormhole_b0, cmd: run_t3000_falcon40b_tests, timeout: 30, owner_id: U053W15B6JF}, #Djordje Ivanovic
           { name: "t3k llama3-small tests", arch: wormhole_b0, cmd: run_t3000_llama3-small_tests, timeout: 30, owner_id: U03PUAKE719},  #Miguel Tairum Cruz
           { name: "t3k llama3.2-11b tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b_tests, timeout: 30, owner_id: U03PUAKE719},  #Miguel Tairum Cruz
-          # { name: "t3k llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y},  #Colman Glagovich
-          # { name: "t3k n300 mesh llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y},  #Colman Glagovich
+          { name: "t3k llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y},  #Colman Glagovich
+          { name: "t3k n300 mesh llama3.2-11b-vision tests", arch: wormhole_b0, cmd: run_t3000_spoof_n300_llama3.2-11b-vision_unit_tests, timeout: 30, owner_id: U03FJB5TM5Y},  #Colman Glagovich
           { name: "t3k llama3.1-70b tests", arch: wormhole_b0, cmd: run_t3000_llama3.1-70b_tests, timeout: 30, owner_id: U03PUAKE719},  #Miguel Tairum Cruz
           { name: "t3k mixtral tests", arch: wormhole_b0, cmd: run_t3000_mixtral_tests, timeout: 30, owner_id: U03PUAKE719}, #Miguel Tairum Cruz
           { name: "t3k grok tests", arch: wormhole_b0, cmd: run_t3000_grok_tests, timeout: 30, owner_id: U03HY7MK4BT}, #Mark O'Connor

diff --git a/.github/workflows/ttnn-run-sweeps.yaml b/.github/workflows/ttnn-run-sweeps.yaml
@@ -349,6 +349,7 @@ on:
           - transformer.split_query_key_value_and_split_heads.split_query_key_value_and_split_heads_kv_input
           - transformer.attention_softmax.attention_softmax
           - transformer.attention_softmax.attention_softmax_
+          - transformer.rotary_embedding.rotary_embedding
           - data_movement.stack.stack_pytorch2
           - data_movement.repeat.repeat_pytorch2
           - data_movement.split.split_pytorch2

diff --git a/.gitmodules b/.gitmodules
@@ -1,6 +1,3 @@
-[submodule "third_party/pybind11"]
-	path = tt_metal/third_party/pybind11
-	url = https://github.com/pybind/pybind11.git
 [submodule "third_party/lfs"]
 	path = tt_metal/third_party/lfs
 	url = https://github.com/tenstorrent-metal/lfs.git

diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -259,18 +259,6 @@ if(ENABLE_TRACY)
     add_link_options(-rdynamic)
 endif()
 
-if(WITH_PYTHON_BINDINGS)
-    # Can't use the `REUSE_FROM` option bc tt_lib and ttnn have different build flags :(
-    add_library(pch_pybinds INTERFACE)
-    target_precompile_headers(
-        pch_pybinds
-        INTERFACE
-            ${PROJECT_SOURCE_DIR}/tt_metal/third_party/pybind11/include/pybind11/operators.h
-            ${PROJECT_SOURCE_DIR}/tt_metal/third_party/pybind11/include/pybind11/pybind11.h
-            ${PROJECT_SOURCE_DIR}/tt_metal/third_party/pybind11/include/pybind11/stl.h
-    )
-endif()
-
 ############################################################################################################################
 # Build subdirectories
 ############################################################################################################################

diff --git a/CODEOWNERS b/CODEOWNERS
@@ -173,10 +173,6 @@ tests/**/dtx/ @mywoodstock @sankarmanoj-tt
 tests/**/*test*conv*.py @mywoodstock @sankarmanoj-tt
 tests/python_api_testing/conv/ @mywoodstock @sankarmanoj-tt
 tests/python_api_testing/unit_testing/fallback_ops @tt-aho
-tests/ttnn/integration_tests/stable_diffusion @esmalTT @uaydonat @mywoodstock
-tests/device_perf_tests/stable_diffusion/test_perf_stable_diffusion.py @esmalTT @uaydonat @mywoodstock
-tests/ttnn/integration_tests/unet @esmalTT @uaydonat @mywoodstock
-tests/nightly/wh_b0_only_eth/experimental/functional_unet @esmalTT @uaydonat @mywoodstock
 scripts/profiler/ @mo-tenstorrent
 scripts/docker @tenstorrent/metalium-developers-infra