Commits · c7f8acd431d70ffef99d9550f51a13c2dc7935bb · OpenDAS / dynamo

10 Feb, 2025 3 commits
- doc: Fix doc links (#149) · c7f8acd4
  Graham King authored Feb 10, 2025
  
  c7f8acd4
- feat: OpenAI compatible http service (#123) · ffc6dde1
  Ryan Olson authored Feb 10, 2025
```
Signed-off-by: Ryan Olson <ryanolson@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  ffc6dde1
- Add rust-toolchain so we're all on the same version (#145) · 9d6643b7
  Graham King authored Feb 10, 2025
  
  9d6643b7
08 Feb, 2025 3 commits
- docs: readme updates · 66f048f6
  Neelay Shah authored Feb 08, 2025
  
  66f048f6
- refactor: Modify rust vllm example to use container · d2e7ae02
  Ryan McCormick authored Feb 07, 2025
```
Co-authored-by: Piotr Tarasiewicz <ptarasiewicz@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  d2e7ae02
- build: Support rebuilding and replacing trtllm backend (#99) · 2cfb1b6d
  Tanmay Verma authored Feb 07, 2025
  
  2cfb1b6d
07 Feb, 2025 3 commits
- feat: vLLM DistributedRuntime Monolith and Disagg Workers Example · 45bc426c
  ptarasiewiczNV authored Feb 08, 2025
```
Co-authored-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  45bc426c
- fix: Fix the test_mock_disaggregated_serving on multi-GPU machines (#117) · 39441642
  Tanmay Verma authored Feb 07, 2025
```
Co-authored-by: Piotr Marcinkiewicz <piotrm@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  39441642
- ci: restrict which branches & paths trigging lab testing (#96) · e03d23c8
  J Wyman authored Feb 07, 2025
  
  e03d23c8
06 Feb, 2025 5 commits
- ci: move file to .github/workflows folder (#125) · d1d2d7e3
  J Wyman authored Feb 06, 2025
  
  d1d2d7e3
- docs: readme + examples (#116) · cdcdce96
  Ryan Olson authored Feb 06, 2025
```
Co-authored-by: aflowers <aflowers@nvidia.com>
```
  cdcdce96
- ci: Remove conflicting paths-ignore from rust action (#122) · c9efcce6
  Ryan McCormick authored Feb 05, 2025
  
  c9efcce6
- add Readme, fix formatting (#120) · b3646497
  Alec authored Feb 05, 2025
```
Co-authored-by: aflowers <aflowers@nvidia.com>
```
  b3646497
- fix: Set default 'latest' tag if git tags fail to get parsed (#118) · 7894967e
  Ryan McCormick authored Feb 05, 2025
  
  7894967e
05 Feb, 2025 5 commits
- add deny.toml, update CI to run license checks (#101) · 0cd5d783
  Alec authored Feb 05, 2025
```
Co-authored-by: aflowers <aflowers@nvidia.com>
```
  0cd5d783
- ci: Add Copyright Verification Scripts w/ Automation (#110) · c9130f8f
  J Wyman authored Feb 05, 2025
  
  c9130f8f
- Added runtime/rust/ATTRIBUTIONS-Rust.md (#115) · 9322edef
  Dmitry Tokarev authored Feb 05, 2025
  
  9322edef
- feat: add python bindings + wheel build (#94) · 03b0101e
  Ryan Olson authored Feb 05, 2025
```
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  03b0101e
- ci: update rust pre-merge checks (#97) · ffbc06cc
  Anant Sharma authored Feb 05, 2025
  
  ffbc06cc
04 Feb, 2025 5 commits
- build: pip based installation of icp and runtime. Also make tritonserver optional · ccfe101e
  Neelay Shah authored Feb 04, 2025
```
Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  ccfe101e
- ci: add rust build and pre-merge checks (#91) · 5701753a
  Anant Sharma authored Feb 04, 2025
  
  5701753a
- fix: Fix the mock disaggregated serving test (#87) · db48e835
  Tanmay Verma authored Feb 03, 2025
  
  db48e835
- chore: updating to mv src directory · b34c6f77
  Neelay Shah authored Feb 03, 2025
  
  b34c6f77
- feat: rust - initial commit · 5ed8c1c0
  Ryan Olson authored Feb 03, 2025
```
the journey begins
```
  5ed8c1c0
03 Feb, 2025 1 commit
- refactor: worker rename to runtime · 4017bd18
  Neelay Shah authored Feb 03, 2025
  
  4017bd18
01 Feb, 2025 4 commits
- Adjustment for multi node benchmark · 8492333b
  Piotr Marcinkiewicz authored Feb 02, 2025
```
Signed-off-by: Piotr Marcinkiewicz <piotrm@nvidia.com>
```
  8492333b
- docs: Add Llama 70B benchmark reproduction and results · 04e50aba
  ptarasiewiczNV authored Feb 01, 2025
```
Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Piotr Marcinkiewicz <piotrm@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  04e50aba
- refactor: Replace trtllm example prints with debug logs · 993954a6
  Ryan McCormick authored Feb 01, 2025
  
  993954a6
- feat(llm): adding initial TRTLLM disaggregation support · deb6c7e8
  ishandhanani authored Feb 01, 2025
```
Co-authored-by: nnshah1 <neelays@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  deb6c7e8
31 Jan, 2025 1 commit
- Increase timeouts on failing tests (#78) · 425be8ad
  glos-nv authored Jan 31, 2025
  
  425be8ad
28 Jan, 2025 1 commit

Clean-up vLLM example to use Operator API (#68) · b9a0ce2c

ptarasiewiczNV authored Jan 28, 2025


Signed-off-by: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>

b9a0ce2c

27 Jan, 2025 1 commit
- refactor: Improve the usage of logging in worker (#29) · 022b6db5
  Tanmay Verma authored Jan 27, 2025
  
  022b6db5
25 Jan, 2025 1 commit
- chore: Update build version to v0.1.1 and add Teardown section to LLM example README (#66) · 1c1bd7da
  Ryan McCormick authored Jan 24, 2025
  
  1c1bd7da
24 Jan, 2025 4 commits
- Add Release badge to README page · 7366d75d
  Meenakshi Sharma authored Jan 24, 2025
```
Signed-off-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>
```
  7366d75d
- docs: Add instructions for multi-node disaggregated deployment · 194abde3
  ptarasiewiczNV authored Jan 24, 2025
```
Signed-off-by: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  194abde3
- docs: Add link to LLM example in top level README (#61) · a8c5637f
  Ryan McCormick authored Jan 24, 2025
  
  a8c5637f
- feat: Add vLLM workers to LLM example (#41) · f6d723f6
  Blazej authored Jan 24, 2025
```
Add example of LLM disaggregated serving
```
  f6d723f6
23 Jan, 2025 3 commits

vLLM example README (#52) · 8980ec37

ptarasiewiczNV authored Jan 23, 2025

Signed-off-by: ptarasiewiczNV <104908264+ptarasiewiczNV@users.noreply.github.com>
Co-authored-by: Piotr Marcinkiewicz <piotrm@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>

8980ec37

fix: encoder repetition typo · 41527a81
Alec authored Jan 23, 2025
```
Co-authored-by: aflowers <aflowers@nvidia.com>
```
41527a81

refactor: openai server skeleton · 607fac29

Neelay Shah authored Jan 22, 2025


Co-authored-by: rmccorm4 <21284872+rmccorm4@users.noreply.github.com>
Co-authored-by: piotrm-nvidia <62554872+piotrm-nvidia@users.noreply.github.com>

607fac29