Commits · 9b2e8f3dd5a4c77ded47e84b396797d3f5c0ced8 · OpenDAS / dynamo

20 Feb, 2026 4 commits

refactor(mocker): modularize into common/scheduler/kv_manager/cache (#6440) · 9b2e8f3d
Yongming Ding authored Feb 20, 2026
```
Signed-off-by: Yongming Ding <yongmingd@nvidia.com>
```
9b2e8f3d
feat: interleaved thinking support in reasoning parser (#6422) · d82b0050
MatejKosec authored Feb 20, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
d82b0050
feat: vllm omni text to video generation pipeline (#6104) · 6dd3ce2e
Ayush Agarwal authored Feb 19, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
6dd3ce2e

feat: e2e mm aware kv cache routing support for trtllm backend (#5480) · 23de4e86

zhongdaor-nv authored Feb 19, 2026


Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
Signed-off-by: Zhongdao Ren <zhongdaor@zhongdaor-mlt.client.nvidia.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Zhongdao Ren <zhongdaor@zhongdaor-mlt.client.nvidia.com>

23de4e86

19 Feb, 2026 5 commits
- feat: Add runtime.endpoint() method to eliminate namespace chaining (#6386) · 0ce3461a
  Tzu-Ling Kan authored Feb 19, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  0ce3461a
- chore: derive router_id and cancellation_token from component instead of plumbing (#6419) · 1549c338
  Yan Ru Pei authored Feb 19, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  1549c338
- feat: add NVTX annotation to KVBM (#6334) · 832bf80a
  Ziqi Fan authored Feb 19, 2026
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
  832bf80a
- chore: Remove ZmqKvEventListener binding and rework standalone TRT-LLM example... · fc229004
  Yan Ru Pei authored Feb 18, 2026
```
chore: Remove ZmqKvEventListener binding and rework standalone TRT-LLM example to use native Python ZMQ (#6164)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  fc229004
- refactor: move per-item stream tracking into RequestGuard (#6355) · c7986b35
  Yan Ru Pei authored Feb 18, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  c7986b35
18 Feb, 2026 17 commits
- feat: glm47 tool parser (#5897) · 33d71102
  Ayush Agarwal authored Feb 18, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
Signed-off-by: Marko Kosec <mkosec@nvidia.com>
Co-authored-by: Matej Kosec <mkosec@nvidia.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
```
  33d71102
- feat: Move ModelDeploymentCard to _internal (#6378) · bc8f1170
  Tzu-Ling Kan authored Feb 18, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  bc8f1170
- chore: gate plotters dependency behind bench feature (#6380) · cf51a0c4
  Yan Ru Pei authored Feb 18, 2026
```
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  cf51a0c4
- fix: remove default-members in workspace (#6279) · aa16ccf5
  Anant Sharma authored Feb 18, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  aa16ccf5
- fix: remove unnecessary cuda synchronize calls in GMS adapters (#6362) · a55b2433
  Schwinn Saereesitthipitak authored Feb 18, 2026
  
  a55b2433
- feat: more flash indexer optimizations (#6305) · c5c6a551
  Yan Ru Pei authored Feb 18, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  c5c6a551
- fix: gate dynamo-memory numa module behind cfg(target_os = linux) (#6354) · 70822f35
  Yan Ru Pei authored Feb 18, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  70822f35
- chore: standardizes Rust-side Dynamo environment variable names (#6358) · 56379dd5
  jh-nv authored Feb 18, 2026
  
  56379dd5
- fix: Remove http temp cancel token, use real one (#6344) · 9a93eb75
  Graham King authored Feb 18, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  9a93eb75
- chore: multimodal endpoint registration via cli modality (#6270) · 2ace5a4a
  Ayush Agarwal authored Feb 17, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  2ace5a4a
- docs: adding readme and agent docs (#6320) · 3081ca17
  Ryan Olson authored Feb 18, 2026
  
  3081ca17
- refactor: dedup memory module with dynamo-memory; re-exports preserve current t… (#6345) · 86892a05
  Ryan Olson authored Feb 18, 2026
```
Co-authored-by: Ryan Olson <rolson@nvidia.com>
Co-authored-by: Olga Andreeva <124622579+oandreeva-nv@users.noreply.github.com>
```
  86892a05
- feat: add MiniMax-M2 reasoning parser and fix tool call parsing (#6294) · 8245633a
  ishandhanani authored Feb 18, 2026
```
Co-authored-by: Claude <noreply@anthropic.com>
```
  8245633a
- feat: add Anthropic Messages API endpoint (/v1/messages) (#6231) · b6603d90
  ishandhanani authored Feb 18, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
Signed-off-by: Marko Kosec <mkosec@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Matej Kosec <mkosec@nvidia.com>
```
  b6603d90
- feat: plumb request priority through sglang and vllm handlers (#6348) · ee0218b5
  Yan Ru Pei authored Feb 17, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
```
  ee0218b5
- feat: add KVBM memory management enhancements (DIS-1311) (#5532) · 976bb70a
  Ryan Olson authored Feb 17, 2026
  
  976bb70a
- fix: wire reasoning parser from worker runtime config into frontend (#6300) · b8c7015f
  MatejKosec authored Feb 17, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  b8c7015f
17 Feb, 2026 1 commit

feat: add prefix groups to rust mooncake bench (#6308) · ef2583a9

Janelle Cai authored Feb 17, 2026


Signed-off-by: Janelle Cai <jcai18@mit.edu>
Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>

ef2583a9

16 Feb, 2026 1 commit
- fix: local block hash consistency in mooncake bench (#6310) · e361d6fa
  Yan Ru Pei authored Feb 16, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  e361d6fa
15 Feb, 2026 1 commit

feat: speculative prefill (#6230) · 4ede59a2

Yan Ru Pei authored Feb 15, 2026


Signed-off-by: PeaBrane <yanrpei@gmail.com>
Co-authored-by: Janelle Cai <jcai18@mit.edu>

4ede59a2

14 Feb, 2026 3 commits
- feat: mm aware routing for vllm (#6235) · 815b1291
  zhongdaor-nv authored Feb 13, 2026
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
```
  815b1291
- feat: kvbm-logical (#6033) · 94fad479
  Ryan Olson authored Feb 13, 2026
```
Signed-off-by: Ryan Olson <rolson@nvidia.com>
```
  94fad479
- fix: tool call validation and stop words. (#5504) · 0e55e821
  Michael Feil authored Feb 13, 2026
```
Signed-off-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
```
  0e55e821
13 Feb, 2026 8 commits
- Rename fetch_llm to fetch_model (#6268) · 5624d144
  Tzu-Ling Kan authored Feb 13, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  5624d144
- docs: update kvbm guide according to docker build change (#6264) · 01426695
  Ziqi Fan authored Feb 13, 2026
```
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
```
  01426695
- chore: allow frontend + mockers to run on macos (#6282) · e30696e5
  Yan Ru Pei authored Feb 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  e30696e5
- fix: consolidate dyn_discovery_backend and dyn_kv_store (#6167) · a289695c
  mohammedabdulwahhab authored Feb 13, 2026
```
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
```
  a289695c
- test: flaky test_sliding_window cache stats test (#6166) · 55a246a3
  Yan Ru Pei authored Feb 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  55a246a3
- ci: add rust check to keep lockfiles updated (#6278) · f308a3d3
  Anant Sharma authored Feb 13, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  f308a3d3
- chore: more mocker rusty cleanups (#6271) · 5a3c52ab
  Yan Ru Pei authored Feb 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  5a3c52ab
- chore: otel tracings for routing overheads and metrics (#6194) · f6c34e07
  Yan Ru Pei authored Feb 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f6c34e07