Skip to content
Open
Changes from all commits
Commits
Show all changes
70 commits
Select commit Hold shift + click to select a range
bede972
feat: add custom gpu type to CRD (#4408)
tmonty12 Nov 18, 2025
cb2f56b
fix: use --num-dataset-entries instead of --conversation-num (#4439)
ajcasagrande Nov 18, 2025
35f2174
feat: support prompt_tokens_details in usage (#4239)
vladnosiv Nov 18, 2025
095d4fd
chore: update aiperf version (#4438)
nv-tusharma Nov 18, 2025
4d48797
fix: respect router env vars in frontend configuration (#4431)
vladnosiv Nov 18, 2025
f474641
fix: guard KV-indexer against self-referential blocks (#4395)
vladnosiv Nov 18, 2025
45391a9
feat: Support a dynamic default max_tokens for VLLM backend (#4156)
flpanbin Nov 18, 2025
7b7c4a5
feat: Support toolcall parser for DeepSeek V3 and R1 (#4253)
tangcy98 Nov 18, 2025
78317be
fix: Recipe namespace fix (#4445)
atchernych Nov 18, 2025
ef8444f
docs: kvbm wheels doc fix (#4455)
oandreeva-nv Nov 19, 2025
9a3281a
fix: Allow users to set `--kv-transfer-config` for vLLM (#4317)
chandlj Nov 19, 2025
559def1
feat: Request Cancellation when transitioning from Prefill to Decode …
kthui Nov 19, 2025
ea1c038
feat: generate deterministic lora id from lora name (#4457)
biswapanda Nov 19, 2025
ec1d6fe
feat: nvext field to OpenAI APIs and add worker_id reporting (vLLM) (…
zhongxuanwang-nv Nov 19, 2025
f6f8364
chore: Unpinned accelerate version (#4458)
krishung5 Nov 19, 2025
7687409
chore: Upgrade NIXL to 0.7.1 and allow KVBM to pick NIXL cuda 12 or 1…
nv-kmcgill53 Nov 19, 2025
96d74fd
ci: TRT-LLM multimodal CI (#4118)
indrajit96 Nov 19, 2025
ce285e5
feat: Only monitor NATS metrics if using NATS request plane (#4442)
grahamking Nov 19, 2025
2662c2a
fix: Update doc to assign port to avoid zmq port collision (#4469)
krishung5 Nov 19, 2025
6556207
fix: Revert "feat: kvbm kernels (#4356)" (#4467)
dmitry-tokarev-nv Nov 19, 2025
ce73574
fix: no build in post-create.sh and document Docker 29.0.x issue (#4376)
keivenchang Nov 19, 2025
2375f73
feat: Enable autodeploy as a backend for TRT-LLM (#4347)
2ez4bz Nov 19, 2025
687da99
fix: fix dgd.yaml (#4471)
mohammedabdulwahhab Nov 19, 2025
7cbc127
feat: unregister discovery instance (#4459)
biswapanda Nov 19, 2025
c294d22
fix: fix trtllm multinode deployment with LWS (#4477)
julienmancuso Nov 19, 2025
a271f4c
feat(mistralrs): Upgrade to support CUDA 13 (#4474)
grahamking Nov 19, 2025
05436e0
fix: fix recipe docs (#4472)
atchernych Nov 19, 2025
fce7fb0
fix: add env var for model (#4475)
atchernych Nov 19, 2025
500a290
fix: support multimodal models with non-standard Jinja2 tags (#4379)
keivenchang Nov 19, 2025
3005672
chore: Remove unused leader_worker_barrier (#4480)
grahamking Nov 19, 2025
73f6e3c
fix: use hf id in dsr1 recipe to support DGDR (#4481)
tedzhouhk Nov 19, 2025
ccddcfd
docs: add Developing Locally section to KVBM runbooks (#4488)
ziqifan617 Nov 20, 2025
64b3fb1
feat: Report KVBM cache hit rate (#4333)
krishung5 Nov 20, 2025
1631b7a
feat: add validation webhooks (#4416)
julienmancuso Nov 20, 2025
ae9460f
test: Router CI tests with vLLM engine (#3948)
karen-sy Nov 20, 2025
13fb713
docs: add documentation for request plane (#4491)
biswapanda Nov 20, 2025
ce79cc4
fix: expose LMCache metrics via Dynamo metrics endpoint (#4461)
keivenchang Nov 20, 2025
1276242
fix: same endpoint for tcp health check (#4494)
biswapanda Nov 20, 2025
fdb8e32
chore: better error handling in Router slot manager (#4496)
PeaBrane Nov 20, 2025
163b82b
chore: update low latency fp8 (#4499)
ishandhanani Nov 20, 2025
a27ac31
docs: update Latest News section in README (#4452)
athreesh Nov 20, 2025
cccd52c
chore: Remove DistributedRuntime::etcd_client (#4489)
grahamking Nov 20, 2025
1170f52
fix(operator): reconcile user made edits on resources (#4470)
tmonty12 Nov 20, 2025
fa8c3ff
ci: Add manual trigger variable (#4490)
pvijayakrish Nov 20, 2025
57d0804
docs: Fix typo in hidden_toctree.rst (#4511)
rmccorm4 Nov 20, 2025
fd34b3b
feat: Add metrics endpoint to kserve gRPC service (#4400)
tanmayv25 Nov 20, 2025
0fcb164
ci: OPS-2134: Add framework builds to nightlies (#4435)
dillon-cullinan Nov 20, 2025
68606ba
fix: [k8s service discovery] only replace service account when one is…
hhzhang16 Nov 20, 2025
a24a6ef
chore: Use general engine source for KVBM KV events (#4515)
krishung5 Nov 20, 2025
2874c1c
fix: Support for msg[content] as a list (#4485)
KrishnanPrash Nov 20, 2025
439a3b6
chore: update model cache pvc name to match recipes (#4506)
tedzhouhk Nov 21, 2025
202c11b
test: parallel mocker tests in CI (#4493)
PeaBrane Nov 21, 2025
6f445f9
ci: Testing b64 multimodal support with real image (#4280)
KrishnanPrash Nov 21, 2025
fd6b9c7
fix: missing tool calling usage (#4516)
ayushag-nv Nov 21, 2025
fb11a83
feat: add an optional PVC mounting option to DGDR for profiling (#4503)
hhzhang16 Nov 21, 2025
1f4be9c
fix: set `SGLANG_BLOCK_NONZERO_RANK_CHILDREN` to be no-op (#4527)
ishandhanani Nov 21, 2025
eb0b511
feat: Xml coder tool parser (#4415)
2ez4bz Nov 21, 2025
9b67925
chore: parallelize planner profile tests + bindings test cleanup (#4532)
PeaBrane Nov 21, 2025
189384f
fix: worker_id updates not applied (#4518)
zhongxuanwang-nv Nov 21, 2025
9824201
chore: merge KvIndexer and ApproxKvIndexer (#4500)
PeaBrane Nov 21, 2025
b3b314e
docs: Add Recipes to ToC and bump FW Support Matrix further up (#4536)
harryskim Nov 21, 2025
8038256
fix: better instructions for GAIE recipe (#4525)
atchernych Nov 21, 2025
05edee8
fix: fix PVC in shared frontend example (#4517)
julienmancuso Nov 21, 2025
0af47c7
chore: split frontend + runtime launch message to accurately represen…
nv-tusharma Nov 21, 2025
74c118c
fix(storage): Correctly encoding FileStore keys (#4539)
grahamking Nov 21, 2025
d6557ea
chore: Make nats_client private at crate level, various tidy up (#4513)
grahamking Nov 21, 2025
7a179de
fix: health check endpoint (#4522)
biswapanda Nov 22, 2025
075db3c
chore: unify LMCache UX w/ and w/o Dynamo (#4509)
ziqifan617 Nov 22, 2025
4ed14c4
chore: upgrade trtllm 1.2.0rc2 (#4405)
dmitry-tokarev-nv Nov 22, 2025
94250ec
Merge branch 'main' into fix_dco_coauthor_for_pr4408
zxue2 Nov 22, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view

These merge commits were added into this branch cleanly.

There are no new changes to show.