Commits · 3188c70a3b3291c614dd1f19076d4759a19a73a5 · OpenDAS / dynamo · GitLab

11 Feb, 2026 10 commits
- chore: Templating Feedback Followup (#6125) · 3188c70a
  Dillon Cullinan authored Feb 11, 2026
```
Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
```
  3188c70a
- fix: added standard assets from NVIDIA fern styling (#6148) · 33ddd8fb
  Ryan Amirthan Stephen authored Feb 11, 2026
```
Signed-off-by: Ryan Amirthan Stephen <105958906+Ryan-Amirthan@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  33ddd8fb
- chore: Merge bindings client and client2 functions (#6158) · 73dc3be8
  Graham King authored Feb 11, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  73dc3be8
- feat: add router-level Prometheus metrics and centralize request tracking (#6146) · f46720c9
  Yan Ru Pei authored Feb 10, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  f46720c9
- feat: support `reasoning_content` context management (DeepSeek v3.2 & GLM-4.7 & Kimi-2.5) (#6107) · 2cee89a0
  Vladislav Nosivskoy authored Feb 11, 2026
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
```
  2cee89a0
- feat: add Prometheus auto and custom label injection for engine metrics (#5989) · e18840ce
  Keiven C authored Feb 10, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  e18840ce
- test: refactor router e2e tests to use context managers for process lifecycle (#6088) · 6fe2152b
  Karen Chung authored Feb 10, 2026
  
  6fe2152b
- chore: add custom fern url (#6111) · 1cd3b724
  Neal Vaidya authored Feb 10, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  1cd3b724
- fix: harden KVBM integration tests with dynamic timeouts and metrics (#6105) · 2eb9e0dd
  Keiven C authored Feb 10, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  2eb9e0dd
- feat: add embedding transfer sender and receiver (#6098) · 67d00b24
  GuanLuo authored Feb 10, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  67d00b24
10 Feb, 2026 29 commits
- refactor: move worker init logic from main.py to workers/ module (#6063) · be9adb34
  Yuewei Na authored Feb 10, 2026
```
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
```
  be9adb34
- fix: add python requirements for vllm tests (#6128) · c8ad4aa6
  Graham King authored Feb 10, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  c8ad4aa6
- chore: remove media-nixl feature (#5940) · bf9e6d04
  milesial authored Feb 10, 2026
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  bf9e6d04
- ci: inline fern publish step into fern-docs workflow (#6091) · 9b1e461e
  Jonathan Tong authored Feb 10, 2026
```
Signed-off-by: Jont828 <jt572@cornell.edu>
```
  9b1e461e
- feat(frontend): Use vllm for pre and post processing (#5544) · 4f99451b
  Graham King authored Feb 10, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  4f99451b
- docs: Add AKS storage guidance for Dynamo caches (#5581) · 93a27308
  devivasudevan authored Feb 10, 2026
```
Signed-off-by: Devi Vasudevan <deviv@microsoft.com>
Signed-off-by: devivasudevan <49675305+devivasudevan@users.noreply.github.com>
Co-authored-by: Sertaç Özercan <852750+sozercan@users.noreply.github.com>
```
  93a27308
- chore: Add deploy as shared code owners on `examples/` folder. (#6133) · 77e7b721
  Graham King authored Feb 10, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  77e7b721
- ci: adding timeouts (#6062) · b6911f78
  Ran Rubin authored Feb 10, 2026
  
  b6911f78
- test: streamline Python test structure (#5684) · bd344cf9
  Qi Wang authored Feb 10, 2026
  
  bd344cf9
- feat: add video diffusion support to TRTLLM backend (wan_t2v only) (#5926) · df2daadd
  Yuewei Na authored Feb 10, 2026
```
Signed-off-by: Yuewei Na <nv-yna@users.noreply.github.com>
Signed-off-by: Yuewei Na <248773860+nv-yna@users.noreply.github.com>
Co-authored-by: Yuewei Na <nv-yna@users.noreply.github.com>
Co-authored-by: Tanmay Verma <tanmayv@nvidia.com>
```
  df2daadd
- fix: scale synthesized data length correctly for expected cache hit stats (#6117) · 8707dc2c
  Karen Chung authored Feb 10, 2026
  
  8707dc2c
- fix: fix cross selection issue amongst services in DGD (#6113) · d8628cc4
  mohammedabdulwahhab authored Feb 10, 2026
```
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
```
  d8628cc4
- fix: prevent aiperf pipe hang in planner scaling test (#6099) · 4ad739dd
  MatejKosec authored Feb 10, 2026
```
Replace PIPE-based stdout/stderr capture with direct file output in LoadGenerator.generate_load() to prevent orphaned aiperf child processes from blocking communicate() indefinitely
Add start_new_session=True so os.killpg() can kill the entire process tree on timeout (not just the main process)
Add unit test validating process-group kill on timeout
Fixes DYN-2086
```
  4ad739dd
- ci: apply static type check to vllm multimodal handlers (#6027) · ae09b929
  Qi Wang authored Feb 10, 2026
  
  ae09b929
- refactor: add prefill_worker_utils in vLLM (#6017) · 20ccc9b2
  Qi Wang authored Feb 10, 2026
  
  20ccc9b2
- 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
- fix: llama4 vllm agg multimodal script (#6103) · 120ae649
  Indrajit Bhosale authored Feb 10, 2026
  
  120ae649
- chore: consistent name -- MultimodalEmbeddingCache (#5962) · df8fd92b
  Qi Wang authored Feb 10, 2026
  
  df8fd92b
- ci: add kvbm bindings to pre merge checks (#6042) · fb62e2cf
  Anant Sharma authored Feb 10, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  fb62e2cf
- feat: base classes for the configuration system (#5975) · bf6840e6
  jh-nv authored Feb 10, 2026
  
  bf6840e6
- feat: Add metric tokenizer_latency_ms (#6092) · f1bcb175
  Graham King authored Feb 10, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  f1bcb175
- fix: sanitize docker tags on main to arm64/amd64 removing 'linux/...' (#6108) · d8feb93c
  Harrison Saturley-Hall authored Feb 10, 2026
  
  d8feb93c
- feat: Dockerfile templating (#5633) · ac020629
  Dillon Cullinan authored Feb 10, 2026
```
Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
```
  ac020629
- fix: increase router E2E timeouts in preparation for enabling xdist (parallel pytest) later (#6085) · 5755a8de
  Keiven C authored Feb 09, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  5755a8de
- fix: test_router_decisions async fix race condition (#6084) · f51ec24d
  Keiven C authored Feb 09, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f51ec24d
- feat: add NIXL check to sanity_check (#6087) · 241cc783
  Keiven C authored Feb 09, 2026
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  241cc783
- feat: expose Python Prometheus metric via DynamoComponentMetrics (#5817) · 027d2653
  Keiven C authored Feb 09, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  027d2653
- feat: Add SGLang /engine weight update endpoints (#6094) · 56a1b6e3
  William Arnold authored Feb 09, 2026
  
  56a1b6e3
- docs: Fix service name in port-forward command (#5527) · 98eb6b7e
  orangeng authored Feb 09, 2026
```
Signed-off-by: Orange Ng <ngquanhao@outlook.com>
Co-authored-by: Neal Vaidya <nealv@nvidia.com>
```
  98eb6b7e
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