Commits · 8e2363758e2bd544a82dd0f2bf9cf33b1097984e · OpenDAS / dynamo

24 Feb, 2026 5 commits
- fix: restore E/P/D multimodal disagg serving and add Qwen3-VL-30B-A3B support (#6533) · 8e236375
  KrishnanPrash authored Feb 24, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
```
  8e236375
- chore: install vllm-omni in vllm container (#6458) · e94f4647
  Ayush Agarwal authored Feb 24, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  e94f4647
- feat: remove --connector flag for vLLM backend (LLM-90) (#6450) · 6d3b92f0
  Alec authored Feb 24, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  6d3b92f0
- feat: embedding cache in agg vLLM node (#6153) · 33b3cb8a
  Qi Wang authored Feb 23, 2026
  
  33b3cb8a
- feat: add --disaggregation-mode enum to vLLM backend (#6483) · 7893f268
  Alec authored Feb 23, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  7893f268
23 Feb, 2026 4 commits
- feat: Remove Component from public (#6403) · 80cac7c1
  Tzu-Ling Kan authored Feb 23, 2026
```
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
```
  80cac7c1
- fix: prefix omni/diffusion CLI flags with --omni- to avoid vLLM collisions (#6476) · 43ce8608
  Alec authored Feb 23, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  43ce8608
- fix(chrek): fix CI errors and replace SIGUSR2 with SIGKILL on checkpoint failure (#6478) · 673822ea
  Schwinn Saereesitthipitak authored Feb 23, 2026
  
  673822ea
- feat: Backend accept new requests during shutdown grace period (#6093) · ea86df29
  jh-nv authored Feb 22, 2026
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  ea86df29
22 Feb, 2026 2 commits

feat: add --headless mode for multi-node TP/PP in dynamo.vllm (#6204) · 4ebb244b

Alec authored Feb 22, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

4ebb244b

fix: add pre_merge markers to vLLM unit tests (#6482) · a9568455

Alec authored Feb 22, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

a9568455

21 Feb, 2026 1 commit
- feat(chrek): external restore, signal-based IPC, and package refactor (#6286) · bb8fc8a4
  Schwinn Saereesitthipitak authored Feb 20, 2026
```
Co-authored-by: Dan Feigin <dfeigin@nvidia.com>
```
  bb8fc8a4
20 Feb, 2026 7 commits
- feat(frontend): Reduce Python-side overhead in the vLLM chat path (#6437) · f91b42b9
  Graham King authored Feb 20, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  f91b42b9
- fix: vllm omni image perf fix (#6451) · 7409bd3a
  Ayush Agarwal authored Feb 20, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  7409bd3a
- feat: add embedding cache to pd worker (#6061) · c82fe888
  Qi Wang authored Feb 20, 2026
  
  c82fe888
- feat: default kv-events-config to empty (align with vLLM defaults) (#6404) · 7bbacce1
  Alec authored Feb 19, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  7bbacce1
- chore: unify filesystem usage across all frameworks and workers (#6391) · d6c49779
  Ayush Agarwal authored Feb 19, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  d6c49779
- 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: TRT-LLM multimodal preprocessor with backend media decoding (#5910) · 8a098a66
  Michal Guzek authored Feb 19, 2026
```
Signed-off-by: Michal Guzek <mguzek@nvidia.com>
```
  8a098a66
19 Feb, 2026 4 commits
- feat: resolve lora request for multimodal workers (#6399) · 026f361d
  Biswa Panda authored Feb 19, 2026
  
  026f361d
- 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
- feat: add model field to multimodal protocol for LoRA identity (#6382) · 4ba48b79
  Biswa Panda authored Feb 19, 2026
  
  4ba48b79
- feat: use embedding transfer classes for EPD (#6223) · a2a6917f
  GuanLuo authored Feb 19, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  a2a6917f
18 Feb, 2026 6 commits
- refactor: introduce worker factory in vLLM multimodal (#6060) · 4d0380d5
  Qi Wang authored Feb 18, 2026
  
  4d0380d5
- fix: remove unnecessary cuda synchronize calls in GMS adapters (#6362) · a55b2433
  Schwinn Saereesitthipitak authored Feb 18, 2026
  
  a55b2433
- feat: add --endpoint flag support to dynamo.vllm (#6360) · 9352da7a
  Alec authored Feb 18, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  9352da7a
- chore: multimodal endpoint registration via cli modality (#6270) · 2ace5a4a
  Ayush Agarwal authored Feb 17, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  2ace5a4a
- 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
- refactor: delete handlers and disagg EC producer/consumer (#6051) · d2a57839
  Qi Wang authored Feb 17, 2026
  
  d2a57839
14 Feb, 2026 2 commits
- feat: migrate SGLang configuration (#6280) · f4f82762
  jh-nv authored Feb 14, 2026
```
Signed-off-by: jh-nv <jihao@nvidia.com>
```
  f4f82762
- 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
13 Feb, 2026 7 commits
- feat: Enable ModelExpress P2P weight transfer in Dynamo vLLM worker (#6186) · 233a1e9a
  Hyunjae Woo authored Feb 13, 2026
```
Signed-off-by: Hyunjae Woo <hwoo@nvidia.com>
```
  233a1e9a
- 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
- fix: consolidate dyn_discovery_backend and dyn_kv_store (#6167) · a289695c
  mohammedabdulwahhab authored Feb 13, 2026
```
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
```
  a289695c
- fix: vLLM decode worker logging format bug causing CrashLoopBackOff (#6267) · 4e50a3f3
  Tushar Sharma authored Feb 13, 2026
```
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  4e50a3f3
- test: vllm conformance tests for the new frontend processing APIs (#6256) · 98df1a2c
  Graham King authored Feb 13, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  98df1a2c
- chore: rename KvPushRouter to KvRouter in python + more bindings removal (#6238) · 14eceb43
  Yan Ru Pei authored Feb 12, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  14eceb43
- feat: add encode client and embedding cache to PD worker (#6029) · cb88fdc7
  Qi Wang authored Feb 12, 2026
  
  cb88fdc7
12 Feb, 2026 2 commits
- feat: Migrate vllm configuration system (#6075) · de27efe6
  jh-nv authored Feb 12, 2026
  
  de27efe6
- feat: request migration for SGLang (#5659) · b94f9dcd
  jh-nv authored Feb 11, 2026
  
  b94f9dcd