Commits · 1af7433bffac503dc3ecbb6834f4baf6e9358c33 · OpenDAS / dynamo

05 Mar, 2025 1 commit
- refactor: rename triton_distributed to dynemo (#22) · 1af7433b
  Neelay Shah authored Mar 05, 2025
```
Co-authored-by: Graham King <grahamk@nvidia.com>
```
  1af7433b
28 Feb, 2025 1 commit
- refactor: use async-openai CompletionRequest (#310) · 9162f3ad
  Paul Hendricks authored Feb 28, 2025
  
  9162f3ad
27 Feb, 2025 3 commits
- refactor: rename ChatCompletionResponseDelta to NvCreateChatCompletionStreamResponse (#292) · 110f3f8c
  Paul Hendricks authored Feb 27, 2025
  
  110f3f8c
- refactor: rename ChatCompletionResponse to NvCreateChatCompletionResponse (#291) · c13ea718
  Paul Hendricks authored Feb 27, 2025
  
  c13ea718
- refactor: rename ChatCompletionRequest to NvCreateChatCompletionRequest (#284) · 96866f43
  Paul Hendricks authored Feb 27, 2025
  
  96866f43
26 Feb, 2025 1 commit
- refactor: using async_openai · 86aff237
  Paul Hendricks authored Feb 26, 2025
```
Co-authored-by: Graham King <grahamk@nvidia.com>
```
  86aff237
25 Feb, 2025 3 commits

feat: tio support preprocessor (#265) · 72064d84

Graham King authored Feb 25, 2025

Add backend type `EngineConfig::StaticCore` that wraps the engine in a preprocessor (prompt templating and tokenization).

Add example engine `echo_core` (`out=echo_core`) which takes and returns tokens. A nice side effect is that it echos the full prompt template with system prompt, whereas `echo_full` echos only user prompt.

![image](https://github.com/user-attachments/assets/27ec0a7b-a27d-4e69-96ea-1ffa0822ea90)

72064d84

ci: Add rust checks to missing directories (#239) · c06b95ff
Ryan McCormick authored Feb 25, 2025
```
Signed-off-by: Ryan McCormick <rmccormick@nvidia.com>
```
c06b95ff

refactor: move libs to lib dir · 08fcd7e9

Neelay Shah authored Feb 24, 2025


Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

08fcd7e9