Bump Dockerfile.ci (2024-08-22) (#10227)

* [🤠]: Howdy folks, let's bump `Dockerfile.ci` to 124bcff !

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix bert flags

Signed-off-by: Oliver Koenig <okoenig@nvidia.com>

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Oliver Koenig <okoenig@nvidia.com>
Co-authored-by: pablo-garay <7166088+pablo-garay@users.noreply.github.com>

.github/workflows/cicd-main.yml

@@ -2061,7 +2061,7 @@ jobs:
     with:
       RUNNER: self-hosted-azure
       SCRIPT: |
-        NVTE_FUSED_ATTN=0 NVTE_FLASH_ATTN=0 python examples/nlp/language_modeling/megatron_bert_pretraining.py \
+        python examples/nlp/language_modeling/megatron_bert_pretraining.py \
         trainer.devices=2 \
         trainer.accelerator=gpu \
         trainer.log_every_n_steps=1 \
@@ -2091,7 +2091,7 @@ jobs:
         model.data.data_prefix=[.5,/home/TestData/nlp/megatron_bert/data/bert/simple_wiki_bert_preproc_text_sentence,.5,/home/TestData/nlp/megatron_bert/data/bert/simple_wiki_bert_preproc_text_sentence] \
         model.data.index_mapping_dir=examples/nlp/language_modeling/bert_index_mappings
 
-        NVTE_FUSED_ATTN=0 NVTE_FLASH_ATTN=0 python examples/nlp/language_modeling/megatron_bert_pretraining.py \
+        python examples/nlp/language_modeling/megatron_bert_pretraining.py \
         trainer.devices=2 \
         trainer.accelerator=gpu \
         trainer.log_every_n_steps=1 \
@@ -2128,7 +2128,7 @@ jobs:
     with:
       RUNNER: self-hosted-azure
       SCRIPT: |
-        NVTE_FUSED_ATTN=0 NVTE_FLASH_ATTN=0 python examples/nlp/language_modeling/megatron_bert_pretraining.py \
+        python examples/nlp/language_modeling/megatron_bert_pretraining.py \
         trainer.devices=2 \
         trainer.accelerator=gpu \
         trainer.log_every_n_steps=1 \
@@ -2159,7 +2159,7 @@ jobs:
         model.data.data_prefix=[.5,/home/TestData/nlp/megatron_bert/data/bert/simple_wiki_bert_preproc_text_sentence,.5,/home/TestData/nlp/megatron_bert/data/bert/simple_wiki_bert_preproc_text_sentence] \
         model.data.index_mapping_dir=examples/nlp/language_modeling/bert_index_mappings
 
-        NVTE_FUSED_ATTN=0 NVTE_FLASH_ATTN=0 python examples/nlp/language_modeling/megatron_bert_pretraining.py \
+        python examples/nlp/language_modeling/megatron_bert_pretraining.py \
         trainer.devices=2 \
         trainer.accelerator=gpu \
         trainer.log_every_n_steps=1 \
@@ -2199,7 +2199,7 @@ jobs:
     with:
       RUNNER: self-hosted-azure
       SCRIPT: |
-        NVTE_FLASH_ATTN=0 NVTE_FUSED_ATTN=0 python examples/nlp/language_modeling/megatron_bert_pretraining.py \
+        python examples/nlp/language_modeling/megatron_bert_pretraining.py \
           trainer.devices=2 \
           trainer.accelerator=gpu \
           trainer.log_every_n_steps=1 \
@@ -2229,7 +2229,7 @@ jobs:
           model.data.data_prefix=[.5,/home/TestData/nlp/megatron_bert/data/bert/simple_wiki_bert_preproc_text_sentence,.5,/home/TestData/nlp/megatron_bert/data/bert/simple_wiki_bert_preproc_text_sentence] \
           model.data.index_mapping_dir=examples/nlp/language_modeling/bert_index_mappings
 
-          NVTE_FLASH_ATTN=0 NVTE_FUSED_ATTN=0 python examples/nlp/language_modeling/megatron_bert_pretraining.py \
+          python examples/nlp/language_modeling/megatron_bert_pretraining.py \
           trainer.devices=2 \
           trainer.accelerator=gpu \
           trainer.log_every_n_steps=1 \

Dockerfile.ci

@@ -34,7 +34,7 @@ WORKDIR /workspace
 # Install NeMo requirements
 ARG TE_TAG=7d576ed25266a17a7b651f2c12e8498f67e0baea
 ARG MODELOPT_VERSION=0.15.0
-ARG MCORE_TAG=2fd6e2b74efca73a1f2d27b89bb5419384b4d3bf
+ARG MCORE_TAG=124bcff2a8153eccea4d7d0e4df5c5562aab50b9
 ARG APEX_TAG=810ffae374a2b9cb4b5c5e28eaeca7d7998fca0c
 RUN \
 --mount=type=bind,source=requirements,target=requirements \