Skip to content

remove environment-specific manifests from public branch; #87

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mkuznet1 wants to merge 13 commits into
base: aicomnet_dev
Choose a base branch
from
Open

remove environment-specific manifests from public branch; #87

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
e53e212
Add TheRock model for validation (#53)
coketaste Dec 2, 2025
9ba9f98
Fix the cleanup (#60)
coketaste Jan 6, 2026
6d7a660
Perf entry superset (#58)
coketaste Jan 15, 2026
7ff689e
Revert "Perf entry superset (#58)" (#66)
gargrahul Jan 17, 2026
9bf6ae6
Fail Check condition update for RPM distro (#64)
shashank-parsi Feb 5, 2026
c6c5f5e
Merge origin/main into coketaste/refactor-dis, keep madengine v2
coketaste Mar 5, 2026
a197d7c
Fixed launcher type issue on k8s
coketaste Mar 5, 2026
5d9ba6f
remove environment-specific manifests from public branch; .gitignore …
mkuznet1 Mar 16, 2026
e648df9
Enhance SLURM job script for improved result staging and aggregation.
mkuznet1 Mar 18, 2026
aa28ae7
Refactor container synchronization logic in ContainerRunner.
mkuznet1 Mar 30, 2026
0f9a40d
Enhance SLURM job script to improve performance value extraction.
mkuznet1 Mar 31, 2026
fa72fa4
Merge branch 'coketaste/refactor-dis' into aicomnet_dev
mkuznet1 Mar 31, 2026
6f6a276
Implement local image management in ContainerRunner.
mkuznet1 Apr 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,6 +130,7 @@ venv/
# model relatives
docker/
scripts/
*.json
.*_env/
.vscode/

Expand All @@ -141,4 +142,4 @@ rocprof_output/
rpd_output/
slurm_output/
MagicMock/
.madengine_session_start
.madengine_session_start
30 changes: 0 additions & 30 deletions manifests/mad.env
View file
Open in desktop

This file was deleted.

114 changes: 0 additions & 114 deletions manifests/run_manifest_primus_2node_qwen_localimage.json
View file
Open in desktop

This file was deleted.

132 changes: 0 additions & 132 deletions manifests/run_manifest_pyt_vllm_dissag_llama-3.1-8b_3node_rdma_localimage.json
View file
Open in desktop

This file was deleted.

11 changes: 9 additions & 2 deletions src/madengine/deployment/kubernetes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3469,6 +3469,8 @@ def _create_failure_record(self, model_info: Dict, build_info: Dict, pod_name: s
nproc_per_node = distributed_config.get("nproc_per_node")
if nproc_per_node is None:
nproc_per_node = int(model_info.get("n_gpus", 1))
# Launcher: use distributed.launcher when set, otherwise "native" for k8s
launcher = normalize_launcher(distributed_config.get("launcher"), "kubernetes")

# Create a record with the same structure as successful runs
# but with performance=0, metric="", and status="FAILED"
Expand All @@ -3495,6 +3497,7 @@ def _create_failure_record(self, model_info: Dict, build_info: Dict, pod_name: s
"git_commit": "",
"machine_name": pod_name,
"deployment_type": "kubernetes",
"launcher": launcher,
"gpu_architecture": "",

# Performance metrics - FAILED
Expand Down Expand Up @@ -3561,6 +3564,8 @@ def _build_common_info_dict(
total_gpus = nnodes * nproc_per_node
gpus_per_node = str(nproc_per_node)
nnodes_str = str(nnodes)
# Launcher: use distributed.launcher when set, otherwise "native" for k8s
launcher = normalize_launcher(distributed_config.get("launcher"), "kubernetes")
result = {
"n_gpus": str(total_gpus),
"nnodes": nnodes_str,
Expand All @@ -3576,7 +3581,7 @@ def _build_common_info_dict(
"git_commit": "",
"machine_name": deployment_id,
"deployment_type": "kubernetes",
"launcher": "native",
"launcher": launcher,
"gpu_architecture": gpu_architecture,
"relative_change": "",
"build_duration": build_info.get("build_duration", ""),
Expand Down Expand Up @@ -3612,6 +3617,8 @@ def _create_multiple_result_row_record(
if nproc_per_node is None:
nproc_per_node = int(model_info.get("n_gpus", 1))

# Launcher: use distributed.launcher when set, otherwise "native" for k8s
launcher = normalize_launcher(distributed_config.get("launcher"), "kubernetes")
result = {
"model": item.get("model", model_info.get("name", "")),
"n_gpus": str(nnodes * nproc_per_node),
Expand All @@ -3628,7 +3635,7 @@ def _create_multiple_result_row_record(
"git_commit": "",
"machine_name": deployment_id,
"deployment_type": "kubernetes",
"launcher": "native",
"launcher": launcher,
"gpu_architecture": item.get("gpu_architecture", ""),
"performance": str(item.get("performance", "")),
"metric": item.get("metric", ""),
Expand Down
Loading