Commits · 88478b4ba359112cd16ae049db3d2efce3223d85 · OpenDAS / dynamo · GitLab

23 Apr, 2026 4 commits
- feat(replay): add agentic trace replay format (#8627) · 88478b4b
  Yan Ru Pei authored Apr 23, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  88478b4b
- fix: harden Rust MediaFetcher agains redirect bypass and DNS rebinding (#8569) · 61b0ffcd
  zhongdaor-nv authored Apr 23, 2026
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
```
  61b0ffcd
- feat: split tokenizer code into dynamo-tokenizers crate (#8185) · 0d635418
  ishandhanani authored Apr 23, 2026
  
  0d635418
- feat: Tier-based KV Routing (#8380) · e3d00b89
  jthomson04 authored Apr 23, 2026
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  e3d00b89
22 Apr, 2026 5 commits
- fix(runtime): stop unconditional NATS connection with --discovery-backend file (#8398) · 6ba534a6
  Biswa Panda authored Apr 22, 2026
  
  6ba534a6
- fix: Remove double tokenization in EPP Integration fixes [DYN-2076] (#8093) · a2a2753d
  atchernych authored Apr 22, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  a2a2753d
- chore: Upgrade ffmpeg to v8.1 (#8452) · 4d5db80a
  Graham King authored Apr 22, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  4d5db80a
- feat: Interface for shared kv cache handling in kv routing (#7536) · b441e26a
  jthomson04 authored Apr 22, 2026
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Ishan Dhanani <ishandhanani@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
```
  b441e26a
- refactor(mocker): replace vllm block manager with kvbm-logical (#8451) · 36b4208e
  Yongming Ding authored Apr 22, 2026
```
Signed-off-by: Yongming Ding <yongmingd@nvidia.com>
Co-authored-by: Ryan Olson <rolson@nvidia.com>
```
  36b4208e
21 Apr, 2026 2 commits
- chore: upgrade modelexpress version (#8336) · 9514236c
  Nate Mailhot authored Apr 21, 2026
```
Signed-off-by: Nate Mailhot <nmailhot@nvidia.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  9514236c
- feat(kv-router): add start positions to flat KV events (#8426) · 4b3cd459
  Yan Ru Pei authored Apr 21, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  4b3cd459
20 Apr, 2026 3 commits
- fix(planner): backfill max_num_batched_tokens from discovery for VirtualConnector (#8042) · 44190094
  jthomson04 authored Apr 20, 2026
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
  44190094
- feat(planner/replay): KV reuse awareness in load + throughput scaling (#8314) · c388483a
  Hongkuan Zhou authored Apr 20, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
```
  c388483a
- feat: add staged frontend gauges (#8162) · 0c98d9a1
  Jie Hao authored Apr 20, 2026
  
  0c98d9a1
17 Apr, 2026 1 commit
- fix(replay/planner): planner-in-the-loop replay diagnostics + planner scaling logics fixes (#8280) · 0c7068dd
  Hongkuan Zhou authored Apr 17, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  0c7068dd
16 Apr, 2026 1 commit
- fix(runtime): lock-free TCP connection pool for OOM prevention and... · 6633be54
  Biswa Panda authored Apr 15, 2026
```
fix(runtime): lock-free TCP connection pool for OOM prevention and inflight/resource-leak fixes (#7806)
```
  6633be54
15 Apr, 2026 6 commits
- feat(planner): add advisory mode for scaling decisions (#8244) · 3da6f4d4
  Hongkuan Zhou authored Apr 15, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  3da6f4d4
- chore: bump dynamo version numbers (#8191) · 01a4b6d6
  Harrison Saturley-Hall authored Apr 15, 2026
  
  01a4b6d6
- fix(replay): drain traffic metrics only on throughput ticks (#8232) · b92c9593
  Hongkuan Zhou authored Apr 15, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  b92c9593
- feat(kv-router): add prompt membership index for scheduler reads (#8175) · 134d484d
  Yan Ru Pei authored Apr 15, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  134d484d
- feat(replay): planner-in-the-loop offline replay (#8187) · 89d67172
  jthomson04 authored Apr 14, 2026
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  89d67172
- fix(trtllm): prevent decode worker segfault on prefill scale-down (#7933) · b13a440e
  MatejKosec authored Apr 14, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  b13a440e
14 Apr, 2026 5 commits
- feat: remove enable_nats usage (#7265) · af0ff07c
  Biswa Panda authored Apr 14, 2026
  
  af0ff07c
- fix(kvbm): set CUDA device per rank before ncclCommInitRank (#8147) · 2263defc
  Alec authored Apr 14, 2026
```
Signed-off-by: Alec Flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  2263defc
- fix(replay): short-circuit .npz planner imports (#8050) · 31909ca3
  Yan Ru Pei authored Apr 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  31909ca3
- fix(kv-router): route pinned requests through scheduler (#8142) · 1142478a
  Yan Ru Pei authored Apr 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  1142478a
- fix(deps): pin mio after lockfile drift (#8080) · 20ce329b
  Yan Ru Pei authored Apr 13, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  20ce329b
13 Apr, 2026 3 commits
- feat: add KV cache transfer estimated latency metric for disaggregated serving (#7590) · 1ebe7060
  Jonathan Tong authored Apr 13, 2026
```
Signed-off-by: Jont828 <jt572@cornell.edu>
Co-authored-by: Hongkuan Zhou <tedzhouhk@gmail.com>
```
  1ebe7060
- fix(kvbm): handle typed KvCacheConnectorConfig in consolidator check (#8117) · edce7d3d
  Alec authored Apr 13, 2026
```
Signed-off-by: Alec Flowers <aflowers@nvidia.com>
```
  edce7d3d
- feat: route requests by device type and load for sglang epd (#7215) · a7d51b39
  Wang, Yi authored Apr 14, 2026
```
Signed-off-by: Wang, Yi <yi.a.wang@intel.com>
```
  a7d51b39
11 Apr, 2026 1 commit
- feat: Request Migration disable on max seq len exceeded (#8020) · f6976e7f
  Jacky authored Apr 10, 2026
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
```
  f6976e7f
08 Apr, 2026 9 commits
- fix(planner): avoid hang in wait_for_scaling_completion when no decision pending (#8008) · cab6323c
  jthomson04 authored Apr 08, 2026
```
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
```
  cab6323c
- feat: adding kvbm-engine (#6773) · 008683d6
  Ryan Olson authored Apr 08, 2026
```
Signed-off-by: Ryan Olson <rolson@nvidia.com>
```
  008683d6
- feat(kvbm): add MLA support for DeepSeek-V2 and extend determinism tests (#7786) · ba34f131
  Olga Andreeva authored Apr 08, 2026
```
Signed-off-by: Olga Andreeva <oandreeva@nvidia.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: wz1qqx <ziqi.wang@novita.ai>
```
  ba34f131
- refactor(3/3): switch dynamo-protocols to upstream async-openai types (#7625) · fd5cc288
  ishandhanani authored Apr 08, 2026
```
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  fd5cc288
- chore: Remove dependency memory -> config (#7993) · 0b7a18ce
  Graham King authored Apr 08, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  0b7a18ce
- fix: dp_rank always 0 in non-KV router mode (#7984) · a210efa6
  ishandhanani authored Apr 08, 2026
  
  a210efa6
- feat(kv-router): split Dynamo-native remote indexer [DYN-2593] (#7973) · 49eb397a
  Yan Ru Pei authored Apr 07, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  49eb397a
- chore: fix bindings typo in comments (#7516) · 06513c9b
  Xianlu Bird authored Apr 08, 2026
```
Signed-off-by: xianlubird <xianlubird@gmail.com>
```
  06513c9b
- fix(nixl): fix iteration_count debug logging in _wait_for_completion_ (#7966) · 88966f02
  MatejKosec authored Apr 07, 2026
```
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
```
  88966f02