Merge branch 'Azure:master' into master

vinil-v · Sep 26, 2022 · 58d38b8 · 58d38b8
2 parents b95e4f0 + e19d061
commit 58d38b8
Show file tree

Hide file tree

Showing 21 changed files with 808 additions and 43 deletions.
diff --git a/experimental/deploy_cycle_slurm_ndv4/config.json b/experimental/deploy_cycle_slurm_ndv4/config.json
@@ -282,6 +282,8 @@
             "azure_ib_link_flapping.nhc",
             "azure_gpu_clock_throttling.nhc",
             "azure_cpu_drop_cache_mem.nhc",
+            "azure_gpu_xid.nhc",
+            "azure_nccl_allreduce.nhc",
             "epilog.sh",
             "run_nhc.sh",
             "kill_nhc.sh",

diff --git a/experimental/deploy_cycle_slurm_ndv4/config_pyxis_enroot.json b/experimental/deploy_cycle_slurm_ndv4/config_pyxis_enroot.json
@@ -306,6 +306,8 @@
             "azure_ib_link_flapping.nhc",
             "azure_gpu_clock_throttling.nhc",
             "azure_cpu_drop_cache_mem.nhc",
+            "azure_gpu_xid.nhc",
+            "azure_nccl_allreduce.nhc",
             "epilog.sh",
             "run_nhc.sh",
             "kill_nhc.sh",