827b8c3e51
feat: KVBM V2 transfer ( #4068 )
...
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
2025-11-12 08:57:02 -08:00
d9b674b868
feat: sglang update to `0.5.3.post4` ( #4227 )
2025-11-11 08:16:39 +00:00
23660bc5c3
chore: update versions for 0.7.0 release ( #4217 )
...
Signed-off-by: Anant Sharma <anants@nvidia.com>
2025-11-10 21:40:06 +00:00
d1cf3c2cf6
ci: Add Fault Tolerance K8s test ( #3801 )
...
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
2025-11-07 15:06:02 -08:00
6afa679c5d
chore: KVBM pip wheel ( #3826 )
...
Signed-off-by: Anant Sharma <anants@nvidia.com>
Co-authored-by: Anant Sharma <anants@nvidia.com>
2025-10-31 14:19:30 -07:00
20d1eb2ee9
feat: exclude k8 FT tests that need custom build from default run ( #4017 )
...
Signed-off-by: tzulingk@nvidia.com <tzulingk@nvidia.com>
2025-10-31 17:15:10 +00:00
8bd37c96d6
refactor: move backend deploy, launch and slurm files from components to examples ( #3849 )
...
Signed-off-by: Anant Sharma <anants@nvidia.com>
2025-10-31 13:09:46 -04:00
5f9d202516
chore: Revert "bump sglang version for 0.6.1 dynamo release ( #3911 )" ( #3994 )
2025-10-30 14:53:57 -07:00
1da9d70ab1
chore: bump nixl verison to 0.7.0 ( #3936 )
...
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
2025-10-30 10:28:17 -07:00
666e4aa76e
chore: bump sglang version for 0.6.1 dynamo release ( #3911 )
...
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
2025-10-29 19:54:22 +00:00
52090e2e76
feat: refactor vllm multimodal example ( #3634 )
...
Signed-off-by: ayushag <ayushag@nvidia.com>
2025-10-29 19:31:06 +00:00
ce576c0c18
docs: add sphinx reredirects extension ( #3962 )
...
Signed-off-by: Anant Sharma <anants@nvidia.com>
2025-10-29 19:00:54 +00:00
9bb1af3376
chore: Update version to 0.6.1 ( #3916 )
...
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
2025-10-27 17:17:26 -04:00
70e32f8401
build: Add prometheus_client dependency for pip install without container ( #3794 )
2025-10-21 17:37:11 -04:00
9a002b30aa
fix: add `--host` to k8s and bump sgl version ( #3666 )
2025-10-16 06:32:36 +00:00
c6e3db5eee
chore: update sglang to 0.5.3.post1 to take advantage of container + doc cleanup ( #3621 )
2025-10-14 23:29:39 +00:00
cd2389baef
chore: pre-0.6.0 activities ( #3592 )
...
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
2025-10-13 17:45:19 -04:00
a3d4684076
ci: TRTLLM & SGLang Unit Tests (for --custom-jinja-template) ( #3472 )
...
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
2025-10-10 15:30:21 -07:00
5c69c11930
chore: upgrade nixl to 0.6.0 ( #3550 )
...
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
2025-10-10 13:18:21 -07:00
51f657570a
feat: sglang prefill router + bump to `0.5.3` ( #3498 )
2025-10-09 23:00:54 +00:00
0aa0768f53
chore: Remove llama.cpp engine ( #3499 )
...
Signed-off-by: Graham King <grahamk@nvidia.com>
2025-10-08 16:44:53 -04:00
ff7d43d087
docs: move doc build dependencies to pyproject.toml ( #3453 )
...
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
2025-10-07 11:55:49 -07:00
ddbb4f50ef
chore: Clean up for sglang multimodal example ( #3420 )
...
Signed-off-by: krishung5 <krish@nvidia.com>
2025-10-06 20:11:49 -07:00
836d74172f
feat: restructure source code for python packaging ( #3201 )
...
Signed-off-by: Anant Sharma <anants@nvidia.com>
2025-10-01 13:15:24 -04:00
9b9536d0d7
feat: make prefill router general ( #3329 )
...
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-09-30 20:38:47 -07:00
0ab6bc2b72
chore: update slurm scrips for better warmup and bump sgl version ( #3291 )
2025-09-30 22:20:11 +00:00
5bb7490448
chore: bump vllm version to 0.10.2 ( #3180 )
...
Signed-off-by: Alec <aflowers@nvidia.com>
Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>
Signed-off-by: krishung5 <krish@nvidia.com>
Co-authored-by: Kris Hung <krish@nvidia.com>
2025-09-26 04:01:57 +00:00
980727bba1
chore: bump versions ahead of 0.5.1 release ( #3209 )
...
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
2025-09-24 18:26:38 -04:00
fb29bd5aea
build: update trtllm to v1.1.0rc5 to enable trtllm + KVBM integration ( #3119 )
...
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
2025-09-19 08:39:49 -07:00
1b2826a987
ci: remove not slow filter ( #2944 )
...
Signed-off-by: alec-flowers <aflowers@nvidia.com>
2025-09-10 20:26:44 -07:00
4b3a2c1a5b
feat: sglang multiple frontend slurm deployment scripts ( #2623 )
...
Signed-off-by: ishandhanani <ishandhanani@gmail.com>
Signed-off-by: Elnifio <elnifio0519@gmail.com>
Co-authored-by: Yunzhou Liu <46603306+Elnifio@users.noreply.github.com>
2025-09-10 19:02:37 +00:00
e8cb972e33
chore: Update trtllm version to 1.1.0rc3 ( #2930 )
...
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
2025-09-09 14:30:02 -07:00
6104c93f35
ci: remove pre-merge ignore in github workflow ( #2940 )
...
Signed-off-by: Anant Sharma <anants@nvidia.com>
2025-09-09 13:25:11 -04:00
9320816275
refactor: standardize e2e tests across 3 frameworks ( #2827 )
...
Signed-off-by: alec-flowers <aflowers@nvidia.com>
2025-09-08 23:31:27 +00:00
fda1efe453
fix: CI is broken with a deprecated dependency on pynvml ( #2926 )
...
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Co-authored-by: alec-flowers <aflowers@nvidia.com>
2025-09-08 22:05:26 +00:00
561ecb98a2
chore: bump version numbers ahead of 0.5.0 release ( #2812 )
...
Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>
2025-09-02 16:13:28 -04:00
135dc82e95
chore: vllm 0.10.1.1 ( #2641 )
2025-08-25 13:13:51 -04:00
9ab37d9445
fix: Update tensorrt_llm to 1.0.0rc6 ( #2606 )
2025-08-21 17:59:09 -07:00
28fb77cf1c
chore: remove circus dependency ( #2602 )
2025-08-21 13:04:50 -07:00
536280fcb6
test: Add deepep test for vllm ( #2534 )
2025-08-19 21:59:24 -04:00
9a02188531
chore: Bumped Dynamo version to 0.4.1 ( #2545 )
2025-08-19 21:55:37 -04:00
5f57ea5fe7
chore: Finish vllm upgrade to 0.10.1 + cleanup ( #2528 )
2025-08-19 19:48:31 +00:00
07cfc3a11b
feat: kvbm + connector ( #2258 )
...
Signed-off-by: Ryan Olson <rolson@nvidia.com>
Co-authored-by: Olga Andreeva <oandreeva@nvidia.com>
Co-authored-by: Ziqi Fan <ziqif@nvidia.com>
Co-authored-by: John Thompson <jothomson@nvidia.com>
Co-authored-by: Richard Huo <rihuo@nvidia.com>
Co-authored-by: Zicheng Ma <zichengm@nvidia.com>
2025-08-19 12:36:53 -07:00
80d8aa19a1
feat(sglang): unify entry point for SGLang backend architecture ( #2493 )
2025-08-18 20:28:12 -07:00
ffae72b7d2
fix: remove kvmanager feature from python 3.12 ai-dynamo-runtime wheel ( #2456 )
2025-08-15 16:43:55 -04:00
ccc8c6270e
feat: Support `python -m dynamo.frontend --version` ( #2449 )
2025-08-15 12:23:36 -04:00
a3d624a726
chore: Rename tensorrtllm framework to trtllm ( #2435 )
2025-08-14 17:13:37 -07:00
9630693e5a
fix: triton ver lock fix and trtllm env var declaration ( #2300 )
2025-08-05 23:49:00 +01:00
625578c3bb
chore: update nixl version to 0.4.1 ( #2221 )
2025-07-31 17:46:21 -04:00
3bf22bb407
feat: reorganize sglang and add expert distribution endpoints ( #2181 )
2025-07-31 18:14:57 +00:00
jthomson04