Commits · f4e208105b3db99e4f79be60fde2b925b8f2b71c · OpenDAS / dynamo

"...git@developer.sourcefind.cn:2222/OpenDAS/vllm_cscc.git" did not exist on "11eddf02f0234f79435d747f2d3dce117ab39aa1"

10 Mar, 2026 1 commit
- fix: Update free_gpu_memory_fraction for llama4 Maverick to avoid OOM in multinode setup (#7090) · f4e20810
  Indrajit Bhosale authored Mar 09, 2026
  
  f4e20810
06 Mar, 2026 3 commits
- fix: [DYN-2335] correct docker tag for tritonserver build (#7037) · e14be96a
  Neal Vaidya authored Mar 06, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
```
  e14be96a
- fix: profiling data format in disagg_planner.yaml (#7019) · fb60cdc5
  Hongkuan Zhou authored Mar 06, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  fb60cdc5
- fix: restore --enforce-disagg to reject requests before prefill router activates (#6957) · f934744f
  Yan Ru Pei authored Mar 05, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f934744f
05 Mar, 2026 4 commits
- chore: Remove llava-hf recipies (#6954) · 7e55a734
  Indrajit Bhosale authored Mar 05, 2026
  
  7e55a734
- chore: add ephemeral-storage requests to deploy profiles (#6723) · 876c9761
  Tushar Sharma authored Mar 05, 2026
```
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  876c9761
- perf: multimodal benchmark sweep (#6795) · 9780bf3a
  Qi Wang authored Mar 04, 2026
  
  9780bf3a
- fix: Skip Encoder llm creation for unsupported models in trtllm (#6866) · f0bfda1e
  Indrajit Bhosale authored Mar 04, 2026
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
  f0bfda1e
04 Mar, 2026 2 commits
- fix: support TRT-LLM 1.3 apply_mm_hashes API (#6810) · d993f9d3
  zhongdaor-nv authored Mar 04, 2026
```
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
```
  d993f9d3
- chore: Optimizations for epp interface complience (#6581) · 73a4ab31
  atchernych authored Mar 03, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  73a4ab31
03 Mar, 2026 8 commits
- fix: properly setup and register vLLM worker for external / hybrid load... · 90d74637
  GuanLuo authored Mar 03, 2026
```
fix: properly setup and register vLLM worker for external / hybrid load balancing. Update launch script (#6695)
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  90d74637
- docs: delete script and add instructions (#6763) · 552ae186
  Qi Wang authored Mar 03, 2026
  
  552ae186
- docs: vLLM README container instructions and KV offloading page (#6793) · 9fe03dd8
  Alec authored Mar 02, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  9fe03dd8
- feat: FlexKV integration in Dynamo (#5858) · 4d7c9845
  Yue Yu authored Mar 03, 2026
```
Signed-off-by: zhuofan1123 <zhuofanl@nvidia.com>
Co-authored-by: zhuofan1123 <zhuofanl@nvidia.com>
```
  4d7c9845
- fix: pass through extra args in trtllm agg.sh launch script (#6787) · 146eb3b4
  KrishnanPrash authored Mar 02, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  146eb3b4
- docs: Refactor TensorRT-LLM backend docs (#6782) · 1bb28d6f
  Tanmay Verma authored Mar 02, 2026
  
  1bb28d6f
- docs: restructure vLLM docs and add startup banners to launch scripts (#6698) · 75bf1e09
  Alec authored Mar 02, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: ishandhanani <ishandhanani@gmail.com>
```
  75bf1e09
- fix: Fix E + PD Multimodal Flow in trtllm (#6726) · 47ed1227
  Indrajit Bhosale authored Mar 02, 2026
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
  47ed1227
02 Mar, 2026 5 commits
- fix: update container image to standard vllm-runtime tag (#6781) · 1bc913ef
  Biswa Panda authored Mar 02, 2026
  
  1bc913ef
- fix: Add weight: 1 to the EPP config plugins (#6756) · ee33acf3
  atchernych authored Mar 02, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  ee33acf3
- fix: disagg_planner.yaml using new planner CLI (#6760) · a3cf35c3
  Hongkuan Zhou authored Mar 02, 2026
```
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
```
  a3cf35c3
- fix(perf): add embedding transfer implementation with NIXL WRITE initiation (#6651) · 2cab0f7f
  GuanLuo authored Mar 02, 2026
```
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
```
  2cab0f7f
- docs: restructure docs directory and move fern config to fern/ (#6700) · ece08dc9
  Neal Vaidya authored Mar 01, 2026
```
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  ece08dc9
27 Feb, 2026 2 commits
- fix: Phase out llava and make EPD single GPU (#6674) · 4ffa1082
  Indrajit Bhosale authored Feb 27, 2026
```
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
```
  4ffa1082
- chore: migrate vllm e/p/d test from gpu_2 -> gpu_1 (#6638) · b1930a61
  KrishnanPrash authored Feb 27, 2026
```
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
```
  b1930a61
26 Feb, 2026 2 commits

chore: add docs for vllm mm router (#6568) · 31642b96

zhongdaor-nv authored Feb 25, 2026


Signed-off-by: zhongdaor <zhongdaor@nvidia.com>
Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

31642b96

feat: enable returning routed experts info up through sglang (#6137) · 4960dbb3
William Arnold authored Feb 25, 2026
```
Signed-off-by: William Arnold <7565007+Aphoh@users.noreply.github.com>
```
4960dbb3

25 Feb, 2026 7 commits
- feat: throughput-metrics-source for SLA planner + GlobalPlanner disagg scaling (#6500) · 651ef5b5
  daiyaanarfeen authored Feb 25, 2026
```
Signed-off-by: Daiyaan <darfeen@nvidia.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
```
  651ef5b5
- fix: migrate example and document to the latest endpoint API (#6542) · 42cde264
  jh-nv authored Feb 25, 2026
  
  42cde264
- docs: embedding cache in vLLM and TRT-LLM (#6555) · d5add7ff
  Qi Wang authored Feb 25, 2026
  
  d5add7ff
- fix: vllm launch script errors for disagg and spec decoding (#6562) · 35323da2
  Alec authored Feb 24, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  35323da2
- fix: add explicit --kv-transfer-config to disagg prefill workers (#6554) · e3dc1793
  Tushar Sharma authored Feb 24, 2026
```
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  e3dc1793
- feat: add --kv-transfer-config NixlConnector to disagg scripts and recipes (#6560) · eac94322
  Alec authored Feb 24, 2026
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
```
  eac94322
- feat: Support epp's "pods" interface in Dynamo fixes [DEP-424] (#6302) · c916cd42
  atchernych authored Feb 24, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  c916cd42
24 Feb, 2026 4 commits

fix: restore E/P/D multimodal disagg serving and add Qwen3-VL-30B-A3B support (#6533) · 8e236375

KrishnanPrash authored Feb 24, 2026


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

8e236375

feat: sglang to 0.5.9 + updated docs (#6518) · 6642e23e

ishandhanani authored Feb 24, 2026


Co-authored-by: baihuitian <baihuitian.bht@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

6642e23e

feat: remove --connector flag for vLLM backend (LLM-90) (#6450) · 6d3b92f0

Alec authored Feb 24, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

6d3b92f0

feat: add --disaggregation-mode enum to vLLM backend (#6483) · 7893f268

Alec authored Feb 23, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

7893f268

23 Feb, 2026 1 commit
- feat: use vllm multiprocessing in multinode scenario (#6191) · 8dd6369e
  Julien Mancuso authored Feb 23, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  8dd6369e
22 Feb, 2026 1 commit

feat: add --headless mode for multi-node TP/PP in dynamo.vllm (#6204) · 4ebb244b

Alec authored Feb 22, 2026


Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

4ebb244b