Commits · 1aab7f6b6d29acb5448c4f6b0ed79eb4a89198b4 · OpenDAS / dynamo

"deploy/vscode:/vscode.git/clone" did not exist on "116b9b4364f11c7f5f14b0a885ca2bdb90664b69"

10 Feb, 2026 1 commit
- fix: use actual service names for profiler logs and handle FileNotFoundError correctly (#6112) · 1aab7f6b
  hhzhang16 authored Feb 10, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  1aab7f6b
09 Feb, 2026 1 commit

fix: profiler deployment timeout handling for MoE models (#6086) · 67329d10

MatejKosec authored Feb 09, 2026

Wrap wait_for_deployment_ready() in try/except TimeoutError for both prefill and decode profiling sweeps
On timeout: log error, record via add_profiling_error(), clean up the timed-out deployment, and continue to the next parallelization mapping
Previously, a single deployment timeout would crash the entire profiler job

67329d10

05 Feb, 2026 1 commit

feat: remove default model name in Profiler; validate for one of served model... · 7e4bc716

hhzhang16 authored Feb 04, 2026


feat: remove default model name in Profiler; validate for one of served model name and model path in Profiler (#5950)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>

7e4bc716

04 Feb, 2026 1 commit
- fix: Add status file to prevent output-copier hang on failures (#5898) · 0268aea4
  hhzhang16 authored Feb 03, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  0268aea4
03 Feb, 2026 1 commit
- fix: check --served-model-name first before --model/--model-path (#5881) · 2b199540
  hhzhang16 authored Feb 02, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  2b199540
14 Jan, 2026 1 commit

feat: SLA Planner configuration support for DEP and TEP VLLM (#4783) · 7cfd966e

MatejKosec authored Jan 14, 2026

Extends the MOE planner profiler to support  TEP (tensor expert parallel) and DEP (data expert parallel) configs with the vllm backend

7cfd966e

12 Jan, 2026 1 commit
- feat: normalize dynamo namespace computation (#5231) · c8770464
  hhzhang16 authored Jan 12, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  c8770464
09 Jan, 2026 1 commit
- feat: mount model path to Profiler if specified (#5212) · ec5630ea
  hhzhang16 authored Jan 09, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  ec5630ea
05 Jan, 2026 1 commit
- feat: support PVC model cache in profiler (#5124) · fbe6bb0a
  Hongkuan Zhou authored Jan 05, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  fbe6bb0a
02 Jan, 2026 1 commit
- chore: update all copyright headers in repo to 2026 (#5130) · cf433e68
  Tushar Sharma authored Jan 02, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  cf433e68
31 Dec, 2025 1 commit
- refactor: preview config in profiler webui use planner dgd generation logic (#4940) · e49834c9
  Hongkuan Zhou authored Dec 31, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  e49834c9
12 Dec, 2025 1 commit
- feat: allow user to input gpu cost in profiler webui (#4935) · b24ccd29
  Hongkuan Zhou authored Dec 12, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  b24ccd29
10 Dec, 2025 1 commit

feat: add webUI to profiler (#4544) · ca0cd3b1

Hongkuan Zhou authored Dec 10, 2025


Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>

ca0cd3b1

03 Dec, 2025 2 commits
- test: add AIConfigurator dense model tests for Dynamo Planner Profiler (#4526) · 2f2a13a3
  Jason Zhou authored Dec 02, 2025
```
Signed-off-by: Jason Zhou <jasonzho@nvidia.com>
```
  2f2a13a3
- chore: clearer prometheus port handling in planner (#4707) · 135bce43
  Hongkuan Zhou authored Dec 02, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  135bce43
02 Dec, 2025 1 commit
- feat: mocker <> planner profiler (#4651) · 2b5655fd
  Hongkuan Zhou authored Dec 02, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  2b5655fd
26 Nov, 2025 1 commit
- feat: support MQA + MoE (Qwen3 MoE) TEP/DEP in Planner Profiler (#4612) · 5652d670
  Hongkuan Zhou authored Nov 25, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  5652d670
17 Nov, 2025 1 commit
- fix: DSR1 DEP Prefill Profiling Benchmark (#4367) · cf97c0dc
  Hongkuan Zhou authored Nov 17, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  cf97c0dc
12 Nov, 2025 1 commit
- fix: typo from mountPoint to mountPath (#4252) · a207b4be
  hhzhang16 authored Nov 12, 2025
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  a207b4be
10 Nov, 2025 3 commits

feat: DynamoPlanner profiler to use hf_id for AIConfigurator 0.4.0 (#4167) · 43986372

Jason Zhou authored Nov 10, 2025


Signed-off-by: Jason Zhou <jasonzho@jasonzho-mlt.client.nvidia.com>
Signed-off-by: Jason Zhou <jasonzho@nvidia.com>
Co-authored-by: Jason Zhou <jasonzho@jasonzho-mlt.client.nvidia.com>

43986372

feat: remove PVC logic from profiler planner (#4210) · fa6a7f94

hhzhang16 authored Nov 10, 2025


Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>

fa6a7f94

feat: support TEP/DEP for DSR1 in SGLang MoE Planner (#4203) · 5e4a339a

Hongkuan Zhou authored Nov 10, 2025

Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

5e4a339a

07 Nov, 2025 1 commit

feat: add parallelization filters (#4144) · 7750ed1a

Hongkuan Zhou authored Nov 07, 2025

Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

7750ed1a

05 Nov, 2025 1 commit
- feat: add cost plot to profiler (#4003) · 0b284b63
  Hongkuan Zhou authored Nov 05, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  0b284b63
04 Nov, 2025 1 commit

feat: use configmap instead of PVC for profiling results (#3981) · d3706221

Hongkuan Zhou authored Nov 04, 2025


Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: Hannah Zhang <hannahz@nvidia.com>

d3706221

03 Nov, 2025 1 commit

feat: grab num_experts info from model info if possible (#4060) · f31a1dad

hhzhang16 authored Nov 03, 2025


Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Hongkuan Zhou <tedzhouhk@gmail.com>

f31a1dad

31 Oct, 2025 2 commits
- fix: reduce max ISL when benchmarking prefill (#4030) · f2414f51
  Hongkuan Zhou authored Oct 31, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  f2414f51
- refactor: move backend deploy, launch and slurm files from components to examples (#3849) · 8bd37c96
  Anant Sharma authored Oct 31, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  8bd37c96
30 Oct, 2025 1 commit
- feat: remove cluster wide logic from namespace restricted operator (#3934) · 6fc4c595
  hhzhang16 authored Oct 30, 2025
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  6fc4c595
29 Oct, 2025 1 commit
- fix: profiler sidecar and other SLA-driven autodeployment fixes (#3932) · a7b703bd
  hhzhang16 authored Oct 28, 2025
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  a7b703bd
27 Oct, 2025 2 commits

feat: turn profiling k8s jobs into sample DGDR requests (#3864) · 6a84ffd3

hhzhang16 authored Oct 27, 2025


Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Hongkuan Zhou <tedzhouhk@gmail.com>

6a84ffd3

refactor: remove hardcoded /workspace paths across tests (#3888) · 07cf0744
Keiven C authored Oct 27, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
07cf0744

23 Oct, 2025 1 commit

feat: automatic profiling config generation (#3787) · a1b38af2

Hongkuan Zhou authored Oct 23, 2025

Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

a1b38af2

17 Oct, 2025 2 commits
- fix: standardize all planner ttft/itl units to float ms and fix docs (#3673) · ee56782b
  William Arnold authored Oct 17, 2025
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
  ee56782b
- fix: json strings should remain intact through profiler arg processing (#3680) · 92064030
  hhzhang16 authored Oct 16, 2025
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  92064030
16 Oct, 2025 2 commits
- fix: git lfs support is erratic with uv so set env var to force it (#3671) · 34fc9693
  Harrison Saturley-Hall authored Oct 16, 2025
```
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  34fc9693
- fix: update invalid AIPerf scripts and parsing logic (#3675) · 333ee983
  Anthony Casagrande authored Oct 16, 2025
```
Signed-off-by: Anthony Casagrande <acasagrande@nvidia.com>
```
  333ee983
15 Oct, 2025 1 commit
- feat: support yaml config input for pre-deployment sweep script (#3622) · 400dceae
  Hongkuan Zhou authored Oct 14, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  400dceae
14 Oct, 2025 2 commits

chore: separate config modifier into multiple files (#3627) · f26d8da7
Hongkuan Zhou authored Oct 14, 2025
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
f26d8da7

feat: update benchmarking script to use aiperf (#3306) · de3ca70b

Biswa Panda authored Oct 13, 2025


Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
Signed-off-by: lkomali <lkomali@nvidia.com>
Co-authored-by: lkomali <lkomali@nvidia.com>
Co-authored-by: Harshini Komali <157742537+lkomali@users.noreply.github.com>

de3ca70b