Commits · a95684559d3cb0f28cf04b6439980806d8ebe35e · OpenDAS / dynamo · GitLab

18 Feb, 2026 1 commit
- 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
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

13 Feb, 2026 1 commit
- 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
10 Feb, 2026 2 commits
- chore: remove media-nixl feature (#5940) · bf9e6d04
  milesial authored Feb 10, 2026
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  bf9e6d04
- feat: Dockerfile templating (#5633) · ac020629
  Dillon Cullinan authored Feb 10, 2026
```
Signed-off-by: Dillon Cullinan <dcullinan@nvidia.com>
```
  ac020629
09 Feb, 2026 1 commit
- fix: DeepSeek V3.2 chat template FC and SO support (#6034) · 7202ced7
  Vladislav Nosivskoy authored Feb 09, 2026
```
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
```
  7202ced7
06 Feb, 2026 1 commit
- chore: clean ups in kv_router.rs (#6028) · 9e33e3fa
  Yan Ru Pei authored Feb 06, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  9e33e3fa
04 Feb, 2026 2 commits
- test: indexer and full router benchmarks (#5784) · 039d35ff
  Janelle Cai authored Feb 04, 2026
  
  039d35ff
- feat: default with lib/memory, media-nixl and kvbm (#5602) · 8daacbd7
  milesial authored Feb 03, 2026
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  8daacbd7
03 Feb, 2026 1 commit
- feat: vLLM backend with frontend media decoding (#5781) · 9bff03f2
  milesial authored Feb 03, 2026
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  9bff03f2
21 Jan, 2026 1 commit
- feat: remove ser/deser in gather_multi_model_data (#5485) · 0f137de4
  milesial authored Jan 21, 2026
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  0f137de4
12 Jan, 2026 1 commit
- fix(llm): Send HF URLs to frontend not full paths (#5290) · f6ae58e3
  Graham King authored Jan 12, 2026
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  f6ae58e3
07 Jan, 2026 1 commit
- fix: vllm default behaviour for generation prompt (#5223) · b5a6b0db
  Ayush Agarwal authored Jan 07, 2026
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  b5a6b0db
02 Jan, 2026 1 commit
- chore: update all copyright headers in repo to 2026 (#5130) · cf433e68
  Tushar Sharma authored Jan 02, 2026
```
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
```
  cf433e68
22 Dec, 2025 1 commit
- feat: add auto-generated frontend OpenAPI spec and helper binary (#4802) · f63e273c
  smatta-star authored Dec 22, 2025
```
Signed-off-by: Satvik Matta <smatta@nvidia.com>
```
  f63e273c
19 Dec, 2025 2 commits
- fix: Replace image_url block with empty image block to render image chat prompt template (#4854) · fc776f7d
  jh-nv authored Dec 19, 2025
```
Signed-off-by: Jie Hao <jihao@nvidia.com>
```
  fc776f7d
- feat: Runtime media decoder config (#5011) · d2faf0e6
  milesial authored Dec 18, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  d2faf0e6
16 Dec, 2025 1 commit
- feat: video decoder in the frontend (#4719) · 74fcd4a9
  milesial authored Dec 16, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  74fcd4a9
12 Dec, 2025 1 commit

feat: DeepSeek V3.2 chat template support (#4797) · 1efc7d63

Vladislav Nosivskoy authored Dec 12, 2025


Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

1efc7d63

05 Dec, 2025 1 commit
- build: Enable frontend decoding (media-nixl) in regular dynamo builds (#4618) · 76f4bc83
  KrishnanPrash authored Dec 05, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  76f4bc83
25 Nov, 2025 1 commit

feat: decoded media via NIXL (#3988) · 0a065918

milesial authored Nov 25, 2025


Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
Signed-off-by: Ayush Agarwal <ayushag@nvidia.com>
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Co-authored-by: Ayush Agarwal <ayushag@nvidia.com>
Co-authored-by: Krishnan Prashanth <kprashanth@nvidia.com>
Co-authored-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>

0a065918

20 Nov, 2025 1 commit

fix: Support for msg[content] as a list (#4485) · 6767559f

KrishnanPrash authored Nov 20, 2025

Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
Signed-off-by: KrishnanPrash <140860868+KrishnanPrash@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

6767559f

19 Nov, 2025 1 commit
- fix: support multimodal models with non-standard Jinja2 tags (#4379) · f395b641
  Keiven C authored Nov 19, 2025
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  f395b641
08 Nov, 2025 2 commits
- fix: deserialize tool call args (#4176) · 51c4fe63
  ryan-lempka authored Nov 07, 2025
```
Signed-off-by: Ryan Lempka <rlempka@nvidia.com>
```
  51c4fe63
- feat: Media decoder and fetcher options in the MDC (#4094) · 14af074e
  milesial authored Nov 07, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  14af074e
07 Nov, 2025 1 commit
- fix: multi-turn bug in should_add_generation_prompt (#4168) · 3fd0ab3d
  ryan-lempka authored Nov 07, 2025
  
  3fd0ab3d
04 Nov, 2025 1 commit
- feat: Image decoder in the frontend (#3971) · ae4b08ac
  milesial authored Nov 04, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  ae4b08ac
31 Oct, 2025 1 commit
- feat: Media HTTP fetching and b64 decoding (#3967) · e30a3054
  milesial authored Oct 31, 2025
```
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
```
  e30a3054
24 Oct, 2025 1 commit

fix: default when tools missing and minijinja length handling (#3880) · 818d72ae

ryan-lempka authored Oct 24, 2025


Signed-off-by: Ryan Lempka <rlempka@nvidia.com>
Signed-off-by: ryan-lempka <rlempka@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

818d72ae

08 Oct, 2025 1 commit
- chore: Remove GGUF support (#3488) · 1b1265e6
  Graham King authored Oct 08, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  1b1265e6
01 Oct, 2025 1 commit
- fix: null tools processing via minijinja (#3340) · 23e79552
  Ayush Agarwal authored Oct 01, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  23e79552
19 Sep, 2025 1 commit
- feat: Convert message[content] from list to string. (#3067) · 5abea1be
  KrishnanPrash authored Sep 19, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  5abea1be
17 Sep, 2025 1 commit
- feat: add chat_template_kwargs param to v1/chat/completion (#3016) · eb6722e3
  Chi McIsaac authored Sep 17, 2025
```
Signed-off-by: Chi McIsaac <chixie.mcisaac@gmail.com>
```
  eb6722e3
16 Sep, 2025 1 commit
- chore(llm): Remove extra license headers (#3065) · bc0a7633
  Graham King authored Sep 16, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  bc0a7633
15 Sep, 2025 1 commit
- fix: Handle invalid JSON in config.json (#3043) · b1186aee
  Graham King authored Sep 15, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  b1186aee
09 Sep, 2025 2 commits
- chore: added tool call schema validation in oai formatter (#2935) · c319aa2d
  Ayush Agarwal authored Sep 09, 2025
```
Signed-off-by: ayushag <ayushag@nvidia.com>
```
  c319aa2d
- feat: Add a checksum to ModelDeploymentCard fields (#2934) · 6f14e941
  Graham King authored Sep 09, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  6f14e941
05 Sep, 2025 1 commit
- fix: Load the tokenizer JSON once for chat and completions. (#2910) · cb5a657a
  Graham King authored Sep 05, 2025
```
Signed-off-by: Graham King <grahamk@nvidia.com>
```
  cb5a657a
03 Sep, 2025 2 commits

refactor: Split ModelType to ModelInput for request and response type;... · 27fad26f

Olga Andreeva authored Sep 03, 2025

refactor: Split ModelType to ModelInput for request and response type; ModelType for the supported workloads (#2714)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Guan Luo <gluo@nvidia.com>
Co-authored-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>

27fad26f

feat: Add --custom-jinja-template argument to pass a custom chat template for vLLM (#2829) · c920cbd9
KrishnanPrash authored Sep 03, 2025
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
c920cbd9