Commits · 8392e7a190505b01d9e07981691b72659d394e3c · OpenDAS / dynamo

"vscode:/vscode.git/clone" did not exist on "49feb28404094d986738d41c63d6f6b64908a858"

27 Jun, 2025 3 commits
- feat: Unnormalize waiting requests + predictive load updates for Python router... · 8392e7a1
  Yan Ru Pei authored Jun 27, 2025
```
feat: Unnormalize waiting requests + predictive load updates for Python router (mirroring Rust) + softmax sampling to reduce thrashing (#1638)
```
  8392e7a1
- fix: remove undefined headless config (#1660) · e53a759c
  GuanLuo authored Jun 26, 2025
  
  e53a759c
- fix: add steps to install using published helm charts (#1623) · 8b1f2ded
  julienmancuso authored Jun 26, 2025
  
  8b1f2ded
26 Jun, 2025 9 commits
- fix: overriding vLLM boolean flags (#1670) · 9f2f95af
  hhzhang16 authored Jun 26, 2025
  
  9f2f95af
- refactor: remove dead protocols code and organize imports idiomatically (#1669) · 9d7c5df5
  Paul Hendricks authored Jun 26, 2025
  
  9d7c5df5
- refactor: Refactor the TRTLLM example components and improve UI (#1654) · 03d976c7
  Tanmay Verma authored Jun 26, 2025
```
Signed-off-by: Tanmay Verma <tanmayv@nvidia.com>
```
  03d976c7
- refactor: removing unsized integer conversions (#1668) · 8a2d6529
  Paul Hendricks authored Jun 26, 2025
  
  8a2d6529
- chore: add exempt issue labels to stale cleaner config (#1617) · d4c2f0a3
  Anant Sharma authored Jun 26, 2025
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  d4c2f0a3
- feat: Add experimental WideEP + EPLB aggregated example for TRTLLM (#1652) · 5fe5a950
  Ryan McCormick authored Jun 27, 2025
  
  5fe5a950
- feat: Set NIXL env vars in ci_minimum and dev images (#1662) · f11fc3f3
  jthomson04 authored Jun 26, 2025
  
  f11fc3f3
- refactor: refactored using CompletionResponse (#1658) · e3f1bd5d
  Paul Hendricks authored Jun 26, 2025
  
  e3f1bd5d
- refactor: refactored using Choice and CompletionFinishReason (#1635) · 7b7b6a6d
  Paul Hendricks authored Jun 26, 2025
  
  7b7b6a6d
25 Jun, 2025 12 commits
- fix: boolean flags can now be set in ServiceConfig (#1630) · c95031ed
  hhzhang16 authored Jun 25, 2025
  
  c95031ed
- fix: fix usage.total_tokens count for OpenAI endpoints (#1649) · 6032c82f
  Zhongdongming Dai authored Jun 25, 2025
  
  6032c82f
- fix: rm curl from api-store image (#1569) · b4aa67a6
  Biswa Panda authored Jun 25, 2025
  
  b4aa67a6
- test: no seed in e2e tests (#1641) · 5960947f
  Yan Ru Pei authored Jun 25, 2025
  
  5960947f
- feat: support batch `/completions` (#1626) · fc16a79b
  ishandhanani authored Jun 25, 2025
```
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  fc16a79b
- fix: add missing await in vllm-v1 `clear_kv_blocks` endpoint (#1642) · 3e1a5534
  Will Killian authored Jun 25, 2025
```
Signed-off-by: Will Killian <wkillian@nvidia.com>
```
  3e1a5534
- chore: Add rmccorm4 to sglang codeowners (#1646) · 34256389
  Ryan McCormick authored Jun 26, 2025
  
  34256389
- fix: remove http endpoint for clearing kv blocks (#1629) · 2d3fb39f
  jain-ria authored Jun 25, 2025
  
  2d3fb39f
- fix: Disable NIXL backend for TRTLLM on ARM (#1639) · e84b1e77
  Tanmay Verma authored Jun 25, 2025
  
  e84b1e77
- feat: Add --version flag to dynamo-run (#1596) · bed8b335
  Nathan Barry authored Jun 25, 2025
  
  bed8b335
- test: several fixes for e2e vllm tests (#1633) · 611722d1
  Yan Ru Pei authored Jun 24, 2025
  
  611722d1
- chore: Add SERVED_MODEL_NAME for consistent model name regardless of MODEL_PATH (#1632) · 2becce56
  Ryan McCormick authored Jun 25, 2025
  
  2becce56
24 Jun, 2025 8 commits
- fix: pin versions on docs dockerfile (#1627) · 57f5725d
  Anant Sharma authored Jun 24, 2025
  
  57f5725d
- refactor: using async_openai::types::Logprobs (#1625) · 0edc886f
  Paul Hendricks authored Jun 24, 2025
  
  0edc886f
- feat: Using NIXL for KV cache transfer when using disaggregated serving in TRTLLM (#1591) · 0b7cdf55
  Tanmay Verma authored Jun 24, 2025
```
Signed-off-by: Tanmay Verma <tanmay2592@gmail.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
```
  0b7cdf55
- refactor: refactoring to use async_openai::types::CompletionUsage (#1397) · 0c9ae4dd
  Paul Hendricks authored Jun 24, 2025
  
  0c9ae4dd
- chore: fix spelling (#1434) · cd18cf2e
  Tianer Zhou authored Jun 24, 2025
```
Signed-off-by: Tianer Zhou <ezhoureal@gmail.com>
Co-authored-by: Yan Ru Pei <yanrpei@gmail.com>
```
  cd18cf2e
- fix: rename create_response_steam to create_response_stream (#1615) · 68e4d2c1
  zxyy-bys authored Jun 24, 2025
  
  68e4d2c1
- chore: Fix failing doctests (#1610) · c3a85c06
  jthomson04 authored Jun 23, 2025
  
  c3a85c06
- feat: Improvements to Leader-Worker barrier (#1498) · 16389141
  jthomson04 authored Jun 23, 2025
  
  16389141
21 Jun, 2025 2 commits
- feat: adding type-erased AnyAsyncEngine (#1601) · 1065ff1a
  Ryan Olson authored Jun 21, 2025
  
  1065ff1a
- docs: Update Discord invite link README.md (#1599) · 9622caaa
  Meenakshi Sharma authored Jun 20, 2025
```
Signed-off-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>
```
  9622caaa
18 Jun, 2025 6 commits
- feat: FT enable DCGM and optional Prometheus and Grafana, plus fixes (#1488) · dd3c470a
  Keiven C authored Jun 18, 2025
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  dd3c470a
- test: Remove completions endpoint from vllm tests. (#1575) · e7cfe0f6
  Pavithra Vijayakrishnan authored Jun 18, 2025
```
Signed-off-by: Pavithra Vijayakrishnan <160681768+pvijayakrish@users.noreply.github.com>
```
  e7cfe0f6
- build(deps): bump protobuf from 5.27.3 to 5.29.5 in /container/deps (#1556) · 2528ea2c
  dependabot[bot] authored Jun 18, 2025
```
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
```
  2528ea2c
- refactor: break profile_sla into different files; feat: support vllm_v1 (#1588) · 7ff10067
  Hongkuan Zhou authored Jun 18, 2025
```
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
```
  7ff10067
- chore: remove unneccssary line (#1582) · d2bec6f8
  tlipoca9 authored Jun 18, 2025
```
Signed-off-by: tlipoca9 <160737620+tlipoca9@users.noreply.github.com>
```
  d2bec6f8
- docs: Fix missing logging import in basic worker example (#1580) · 316dffc0
  Shriyash.Patil authored Jun 18, 2025
```
Signed-off-by: Shriyash.Patil <shriyash81@gmail.com>
```
  316dffc0