Commits · 3d62cc7fd96990c5b97f22755de9eb5ce6487c3c · OpenDAS / dynamo

"vllm/vscode:/vscode.git/clone" did not exist on "51ff154639a31973e6a33fa6208c2b50a88d62e2"

28 Jan, 2026 8 commits
- fix: avoid Prometheus collisions via multi-registry scrape (#5678) · 3d62cc7f
  Keiven C authored Jan 28, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  3d62cc7f
- docs: remove incorrect HighConfidence dLLM algorithm reference (#5723) · ed5e4fd0
  ishandhanani authored Jan 28, 2026
```
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  ed5e4fd0
- chore: make core kv-router its own crate (#5677) · 649d9b7d
  Yan Ru Pei authored Jan 28, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  649d9b7d
- chore: bump vLLM to 0.14.1 (#5691) · 63bee8b3
  Alec authored Jan 27, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
```
  63bee8b3
- feat: global router for hierarchical planner (#5697) · 8ebfd1e4
  Hongkuan Zhou authored Jan 27, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  8ebfd1e4
- chore: add multimodal image benchmark scripts for performance evaluation (#5509) · 903f8184
  GuanLuo authored Jan 27, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  903f8184
- docs: DYN-1967 update metrics docs after kvstats removal (#5704) · 8e72fb69
  Keiven C authored Jan 27, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  8e72fb69
- fix: correct SGLang metrics prefix from sglang_ to sglang: (#5701) · e5557803
  Keiven C authored Jan 27, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  e5557803
27 Jan, 2026 16 commits
- chore: Bump rust lib oneshot to 0.1.13 (#5694) · 2d6babe5
  Dmitry Tokarev authored Jan 27, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  2d6babe5
- chore: Fix tests logging setup (#5693) · 90b07594
  Graham King authored Jan 27, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  90b07594
- chore: type ZmqMessage (#5689) · 382a26f0
  Yan Ru Pei authored Jan 27, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  382a26f0
- feat: implement EncoderCacheManager (#5632) · 4636ecaf
  Qi Wang authored Jan 27, 2026
  
  4636ecaf
- fix: add recv timeout for zmq transport (#5685) · bc76247d
  Biswa Panda authored Jan 27, 2026
  
  bc76247d
- fix: link checking (#5209) · 9c71f286
  Nate Mailhot authored Jan 27, 2026
  
  9c71f286
- ci: update runners in ci-test-suite (#5680) · ce570d31
  Ran Rubin authored Jan 27, 2026
  
  ce570d31
- feat: convert NAT trace to mooncake-style trace (#5675) · e00ada20
  Yan Ru Pei authored Jan 26, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  e00ada20
- fix: Update the vllm docker image to use the cuda sampler rather than the pytorch one (#5613) · f9858193
  Kyle McGill authored Jan 26, 2026
  
  f9858193
- test: radix tree benchmarks (#5617) · ca63c49d
  Janelle Cai authored Jan 26, 2026
  
  ca63c49d
- feat: add ZMQ transport and its discovery (#5625) · 8fc70f20
  Biswa Panda authored Jan 26, 2026
  
  8fc70f20
- test: consolidate guided decoding vLLM configs (#5670) · 2dbfed89
  Alec authored Jan 26, 2026
  
  2dbfed89
- fix: remove cupy-cuda13x from dev container (#5669) · 8d9ccdfb
  Keiven C authored Jan 26, 2026
```
Signed-off-by: Keiven Chang <keivenc@nvidia.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  8d9ccdfb
- feat: request migration for trtllm (#5599) · a9b74dc2
  jh-nv authored Jan 26, 2026
  
  a9b74dc2
- chore: version update for 0.9.0 (#5661) · 66c36996
  Pavithra Vijayakrishnan authored Jan 26, 2026
```
Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
```
  66c36996
- fix: sglang version in build.sh and docs (#5665) · 546f1bbc
  Dmitry Tokarev authored Jan 26, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  546f1bbc
26 Jan, 2026 16 commits
- feat: sglang update to 0.5.8 (#5655) · 4f981e28
  ishandhanani authored Jan 26, 2026
  
  4f981e28
- chore: do not default to privileged mode when mounting workspace. (#5644) · 65a37708
  jh-nv authored Jan 26, 2026
  
  65a37708
- chore: use aic release/0.6.0 (#5600) · aecf0051
  Jason Zhou authored Jan 26, 2026
  
  aecf0051
- fix: Add cupy-cuda12x to sglang extras (#5627) · 76fbbc8f
  Aditya Shrish Puranik authored Jan 26, 2026
```
Signed-off-by: Aditya Puranik <adityapuranik99@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
```
  76fbbc8f
- feat: vLLM integrations for GPU Memory Service (#5615) · ccd12d1c
  Schwinn Saereesitthipitak authored Jan 26, 2026
  
  ccd12d1c
- chore: remove legacy KVBM pythong static type checks and test (#5486) · 89e135b9
  Qi Wang authored Jan 26, 2026
  
  89e135b9
- docs: migrate existing docs to fern (#5445) · f9050aae
  Jonathan Tong authored Jan 26, 2026
```
Signed-off-by: Jont828 <jt572@cornell.edu>
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
Co-authored-by: Neal Vaidya <nealv@nvidia.com>
```
  f9050aae
- docs: reduce admonition clutter in reference docs (#5646) · f238d23a
  dagil-nvidia authored Jan 26, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  f238d23a
- feat: handle PrefillComplete in the Dynamo EPP Scorer Plugin [DEP-728] (#5592) · 2a2e63a0
  atchernych authored Jan 26, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  2a2e63a0
- docs: add release-artifacts.md with comprehensive artifact inventory (#5619) · 24807345
  dagil-nvidia authored Jan 26, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Signed-off-by: dagil-nvidia <dagil@nvidia.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  24807345
- feat: MiniMax tool parser (#5549) · 11d9cdfb
  Ayush Agarwal authored Jan 26, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  11d9cdfb
- fix: Pass empty tokens for new requests for TRTLLM (#5620) · 22fbc022
  Kris Hung authored Jan 26, 2026
  
  22fbc022
- fix(sglang): use correct API and deps for memory occupation endpoints (#5635) · fbf91daf
  Schwinn Saereesitthipitak authored Jan 26, 2026
  
  fbf91daf
- refactor: rename sleep/wake endpoints for consistency (#5629) · f976f02b
  Schwinn Saereesitthipitak authored Jan 26, 2026
  
  f976f02b
- ci: Prod Runners (#5534) · 3d8c497e
  Ran Rubin authored Jan 26, 2026
```
Replacing infra for Github runners
```
  3d8c497e
- test: unit test TCP client handle_reader [2/n] (#5056) · 2a2ad756
  Qi Wang authored Jan 25, 2026
  
  2a2ad756