Commits · bae25dc6d4dfda286d988b0c9396a996e35c212f · OpenDAS / dynamo · GitLab

31 Jul, 2025 1 commit
- feat: skip downloading model weights if using mocker (only tokenizer) (#2213) · bae25dc6
  Yan Ru Pei authored Jul 31, 2025
  
  bae25dc6
30 Jul, 2025 1 commit
- chore: Version bump to 0.4.0 (#2179) · 4c90b1b9
  Dmitry Tokarev authored Jul 30, 2025
  
  4c90b1b9
28 Jul, 2025 4 commits
- chore: Add Request Migration docs and minor enhancements (#2038) · fdcf611f
  Jacky authored Jul 28, 2025
  
  fdcf611f
- feat: updates to structured logging (#2061) · 0cb01b3f
  Neelay Shah authored Jul 28, 2025
```
Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
```
  0cb01b3f
- feat: proper local hashes for mockers + router watches endpoints (#2132) · 803bfa81
  Yan Ru Pei authored Jul 28, 2025
  
  803bfa81
- feat: Base metrics: add generic ingress handler metrics (#2090) · 615580d8
  Keiven C authored Jul 28, 2025
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  615580d8
26 Jul, 2025 1 commit
- refactor: Move engine and publisher from dynamo.llm.tensorrt_llm to dynamo.trtllm (#2128) · 222245e2
  Tanmay Verma authored Jul 25, 2025
  
  222245e2
25 Jul, 2025 1 commit
- fix: move docker-compose.yml to deploy/, and update frontend port (#2121) · 4498a77d
  Keiven C authored Jul 25, 2025
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  4498a77d
24 Jul, 2025 3 commits
- test: add router e2e test with mockers to per-merge ci (#2073) · ba3ac235
  Yan Ru Pei authored Jul 24, 2025
```
Signed-off-by: Yan Ru Pei <yanrpei@gmail.com>
```
  ba3ac235
- feat: dump radix tree as router events (#2057) · 2fc65ad8
  Yan Ru Pei authored Jul 24, 2025
  
  2fc65ad8
- chore(dynamo-run): Remove out=sglang|vllm|trtllm (#1920) · 19a77ae7
  Graham King authored Jul 23, 2025
  
  19a77ae7
23 Jul, 2025 7 commits
- docs: Update docs for new UX (#2070) · 3c500ae7
  Graham King authored Jul 23, 2025
  
  3c500ae7
- feat: query instance_id based on routing strategy (#1787) · f3d784f3
  Biswa Panda authored Jul 23, 2025
  
  f3d784f3
- fix: updates versions and adds ahashmap to BPE (#2072) · 66b7d2c7
  Paul Hendricks authored Jul 23, 2025
  
  66b7d2c7
- fix: endpoint changes should be prioritized over new requests in kv scheduler (#2071) · ffb54096
  Yan Ru Pei authored Jul 23, 2025
```
Signed-off-by: Yan Ru Pei <yanrpei@gmail.com>
```
  ffb54096
- feat: Connect Library (#1478) · e0a51940
  J Wyman authored Jul 23, 2025
  
  e0a51940
- fix: cryptic error message for empty messages list in /chat/completions #2067 (#2067) · 6a69ef4f
  heisenberglit authored Jul 23, 2025
  
  6a69ef4f
- feat: health check changes based on endpoint served (#1996) · b127d95f
  Neelay Shah authored Jul 22, 2025
  
  b127d95f
22 Jul, 2025 3 commits
- chore: Remove unused portion of kv bindings test (#2052) · 9f2356cb
  Ryan McCormick authored Jul 22, 2025
  
  9f2356cb
- feat: use atomic transactions when creating etcd kv (#2044) · 78826932
  Yan Ru Pei authored Jul 22, 2025
  
  78826932
- feat: add a hierarchical Prometheus MetricsRegistry trait for... · e5a8628f
  Keiven C authored Jul 22, 2025
```
feat: add a hierarchical Prometheus MetricsRegistry trait for DistributedRuntime, Namespace, Components, and Endpoint (#2008)
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Ryan Olson <rolson@nvidia.com>
```
  e5a8628f
18 Jul, 2025 4 commits
- feat: http disconnects (#2014) · 343a4814
  Ryan Olson authored Jul 18, 2025
  
  343a4814
- feat: enable / disable chunked prefill for mockers (#2015) · e330d969
  Yan Ru Pei authored Jul 18, 2025
```
Signed-off-by: Yan Ru Pei <yanrpei@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
```
  e330d969
- feat: Add migration to LLM requests (#1930) · 1f07dab7
  Jacky authored Jul 18, 2025
  
  1f07dab7
- feat(frontend): router-mode settings (#2001) · fc124360
  Graham King authored Jul 18, 2025
  
  fc124360
17 Jul, 2025 4 commits
- fix: Fix syntax for tokio-console (#1997) · f3fb09e4
  Kris Hung authored Jul 17, 2025
  
  f3fb09e4
- feat(runtime): Support tokio-console (#1986) · 1eadc013
  Graham King authored Jul 17, 2025
  
  1eadc013
- feat: support separate chat_template.jinja file (#1853) · b62e633c
  GuanLuo authored Jul 17, 2025
  
  b62e633c
- feat: record + analyze logprobs (#1957) · 49b7a0d9
  Ryan Olson authored Jul 17, 2025
  
  49b7a0d9
16 Jul, 2025 3 commits
- chore(bindings): Remove mistralrs / llama.cpp (#1970) · 182d3b5d
  Graham King authored Jul 16, 2025
  
  182d3b5d
- feat: integrate mocker with dynamo-run and python cli (#1927) · f31732a2
  Yan Ru Pei authored Jul 16, 2025
  
  f31732a2
- perf(router): Remove lock from router hot path (#1963) · aba60996
  Graham King authored Jul 16, 2025
  
  aba60996
15 Jul, 2025 4 commits
- chore: Move examples/cli to lib/bindings/examples/cli (#1952) · 7b9182fd
  Graham King authored Jul 15, 2025
  
  7b9182fd
- feat: adding http clients and recorded response stream (#1919) · a9e0891c
  Ryan Olson authored Jul 15, 2025
  
  a9e0891c
- fix: Remove OpenSSL dependency, use Rust TLS (#1945) · 4da078b8
  Graham King authored Jul 15, 2025
  
  4da078b8
- chore: metrics endpoint variables renamed from HTTP_SERVER->SYSTEM (#1934) · 860f3f75
  Keiven C authored Jul 14, 2025
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  860f3f75
14 Jul, 2025 3 commits
- fix: resolve incorrect finish reason propagation (#1857) · 053041e6
  Jorge António authored Jul 15, 2025
  
  053041e6
- feat: prefill aware routing (#1895) · df91fce2
  Yan Ru Pei authored Jul 14, 2025
  
  df91fce2
- chore: envvars for http paths and live health endpoint (#1846) · c7080419
  Greg Clark authored Jul 14, 2025
```
Signed-off-by: Greg Clark <grclark@nvidia.com>
```
  c7080419
11 Jul, 2025 1 commit
- chore: update nixl to 0.4.0 release (#1860) (#1886) · d975761b
  Anant Sharma authored Jul 11, 2025
  
  d975761b