Commits · 72ec5f5c7b9e3d482faa3485fa81994e99d33b22 · OpenDAS / dynamo

13 Aug, 2025 3 commits
- feat: Allow an endpoint to serve multiple models (#2418) · 72ec5f5c
  Graham King authored Aug 13, 2025
  
  72ec5f5c
- chore: update wideep dockerfile for sgl to newest rel (#2422) · ebc84d6c
  ishandhanani authored Aug 12, 2025
  
  ebc84d6c
- feat: support sglang in sla planner (#2421) · e22f84ab
  Hongkuan Zhou authored Aug 12, 2025
```
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
```
  e22f84ab
12 Aug, 2025 2 commits
- feat: Add performance sweeps for DeepSeek R1 on GB200 (#2387) · 1327e3bb
  Tanmay Verma authored Aug 12, 2025
  
  1327e3bb
- feat: support SGLang in pre-deployment sweeping (#2360) · b4189c68
  Hongkuan Zhou authored Aug 12, 2025
```
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
```
  b4189c68
11 Aug, 2025 3 commits
- docs: add sglang installation variants (#2400) · d51580a4
  ishandhanani authored Aug 11, 2025
  
  d51580a4
- fix: use default batch_size for decode (#2376) · 43854732
  Neal Vaidya authored Aug 10, 2025
  
  43854732
- docs: add sglang hicache example and guide (#2388) · 3b722842
  Faradawn Yang authored Aug 10, 2025
  
  3b722842
07 Aug, 2025 3 commits
- feat: Router replicas with state-sharing (#2264) · 5166a3dd
  Yan Ru Pei authored Aug 07, 2025
  
  5166a3dd
- feat: DIS-323 [trtllm backend publisher] only publish kv event with the... · 2cf67765
  Richard Huo authored Aug 06, 2025
```
feat: DIS-323 [trtllm backend publisher] only publish kv event with the biggest window size to support kv routing with variable sliding window attention (#2241)
```
  2cf67765
- feat: LMCache integration in newest ux (#2079) · 784da90e
  ZichengMa authored Aug 06, 2025
```
Signed-off-by: ZichengMa <zichengma1225@gmail.com>
Co-authored-by: Ziqi Fan <ziqif@nvidia.com>
```
  784da90e
06 Aug, 2025 4 commits
- fix: upgrade axum to 0.8 and etcd-client to 0.16 (#2317) · b2aa504b
  Dan Aloni authored Aug 06, 2025
```
Signed-off-by: Dan Aloni <dan.aloni@vastdata.com>
```
  b2aa504b
- feat: Support static workers, run without etcd. (#2281) · 6a1a801c
  Graham King authored Aug 06, 2025
  
  6a1a801c
- fix: Move register_llm_block down (#2316) · 8291172f
  Chi authored Aug 05, 2025
  
  8291172f
- feat: Multimodal support for dynamo with trtllm backend (#2195) · 12fe3551
  Indrajit Bhosale authored Aug 05, 2025
  
  12fe3551
05 Aug, 2025 7 commits
- docs: use prebuilt gpt-oss container (#2313) · 3a425209
  Neal Vaidya authored Aug 05, 2025
  
  3a425209
- docs: fix issues in gpt-oss guide (#2304) · bc3456b4
  Neal Vaidya authored Aug 05, 2025
  
  bc3456b4
- feat: migrate requests when planner shutdown decode engine (vllm) (#2280) · 36c4ef5e
  Hongkuan Zhou authored Aug 05, 2025
```
Signed-off-by: Hongkuan Zhou <tedzhouhk@gmail.com>
Co-authored-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
```
  36c4ef5e
- docs: add TRTLLM variable sliding window attention example for gemma3 model (#2134) · c8f6d4d9
  Richard Huo authored Aug 05, 2025
  
  c8f6d4d9
- docs: add GPT-OSS deployment guide (#2297) · 8964d0d5
  Neal Vaidya authored Aug 05, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: jthomson04 <jwillthomson19@gmail.com>
Co-authored-by: John Thomson (DLAlgo) <jothomson@nvidia.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  8964d0d5
- fix: Adjust frontEnd thrasholds (#2288) · 78ffe3d3
  atchernych authored Aug 04, 2025
  
  78ffe3d3
- fix: Update disagg configs for trtllm 1.0.0rc4 changes (main) (#2278) (#2282) · d537378a
  Ryan McCormick authored Aug 04, 2025
  
  d537378a
04 Aug, 2025 4 commits
- ci: fix sglang paths for nightly (#2275) · 8f005a61
  ishandhanani authored Aug 04, 2025
  
  8f005a61
- chore: sglang k8s health/live, update doc (#2272) · 26dc6281
  Hongkuan Zhou authored Aug 04, 2025
  
  26dc6281
- fix: readme instructions for worker running (#2266) · 053ac33e
  ishandhanani authored Aug 04, 2025
  
  053ac33e
- docs: Remove `TRTLLM_USE_NIXL_KVCACHE` and `TRTLLM_USE_UCX_KVCACHE` environment variables (#2231) · dbb4caaf
  KrishnanPrash authored Aug 03, 2025
  
  dbb4caaf
03 Aug, 2025 1 commit
- docs(sglang): remove note about placeholder metrics implementation (#2256) · e5fa8b62
  ishandhanani authored Aug 02, 2025
  
  e5fa8b62
02 Aug, 2025 1 commit

atchernych authored Aug 01, 2025


Signed-off-by: Anish <80174047+athreesh@users.noreply.github.com>
Co-authored-by: Anish <80174047+athreesh@users.noreply.github.com>

fa492bb1

01 Aug, 2025 4 commits
- feat: sglang + gb200 (#2223) · 959f810f
  ishandhanani authored Aug 01, 2025
  
  959f810f
- test: Request Migration Docs and E2E vLLM Tests (#2177) · ae51b3f4
  Jacky authored Aug 01, 2025
```
Signed-off-by: Jacky <18255193+kthui@users.noreply.github.com>
Co-authored-by: Neelay Shah <neelays@nvidia.com>
```
  ae51b3f4
- feat: add sgl deploy readme (#2238) · 1ad6abed
  ishandhanani authored Jul 31, 2025
  
  1ad6abed
- fix: frontend metrics to be renamed from nv_llm_http_service_* => dynamo_frontend_* (#2176) · 8c75ed79
  Keiven C authored Jul 31, 2025
```
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  8c75ed79
31 Jul, 2025 6 commits
- fix: Add default configs in LLMAPI. Fixes OOM issues (#2198) · 7e3b3fab
  Tanmay Verma authored Jul 31, 2025
  
  7e3b3fab
- feat: reorganize sglang and add expert distribution endpoints (#2181) · 3bf22bb4
  ishandhanani authored Jul 31, 2025
  
  3bf22bb4
- fix: Migrating trtllm examples from `1.0.0rc0` to `1.0.4rc4` (#2217) · f10aab3b
  KrishnanPrash authored Jul 31, 2025
  
  f10aab3b
- fix(k8s): sglang disagg now uses decode worker (#2206) · 97390ac0
  ishandhanani authored Jul 30, 2025
  
  97390ac0
- fix: update SGLang version in instructions and Dockerfile to revert to 0.4.8.post1 (#2204) · c546b630
  ishandhanani authored Jul 30, 2025
  
  c546b630
- feat: Add trtllm deploy examples for k8s (#2133) · f8b0a5a9
  Tanmay Verma authored Jul 30, 2025
```
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
```
  f8b0a5a9
30 Jul, 2025 2 commits
- fix: add better port logic (#2175) · b69c5079
  Alec authored Jul 30, 2025
  
  b69c5079
- chore: address QA broken links comments (#2184) · dabfea3d
  Anish authored Jul 30, 2025
  
  dabfea3d