b6603d90d6
feat: add Anthropic Messages API endpoint (/v1/messages) ( #6231 )
...
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
Signed-off-by: Marko Kosec <mkosec@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Matej Kosec <mkosec@nvidia.com>
2026-02-18 06:11:52 +00:00
8cb47d04d2
feat: responses API compliance with upstream type alignment ( #6089 )
...
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
Co-authored-by: Ishan Dhanani <ishandhanani@gmail.com>
2026-02-12 01:18:28 +00:00
e18840cef3
feat: add Prometheus auto and custom label injection for engine metrics ( #5989 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
2026-02-10 21:22:53 -08:00
0d3ff44000
fix: enable toggling kv events pub/sub (currently nats based) with --no-kv-events flag ( #5237 )
2026-01-09 06:36:51 +00:00
cf433e6825
chore: update all copyright headers in repo to 2026 ( #5130 )
...
Signed-off-by: Tushar Sharma <tusharma@nvidia.com>
2026-01-02 22:08:23 +00:00
6da23fcf79
test: make serve tests xdist-safe with dynamic ports ( #4951 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-12-16 09:15:24 -08:00
f57fd72f88
feat: Add logprobs support to vLLM backend ( #4683 ) ( #4697 )
...
Signed-off-by: Aryan Bagade <aryan@aryanbagade.com>
Signed-off-by: Aryan Bagade <73382554+AryanBagade@users.noreply.github.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
2025-12-10 04:28:33 +00:00
01bfbea15f
feat: Add logprobs support to TRTLLM backend ( #4759 )
...
Signed-off-by: Elijah Soba <esoba@nvidia.com>
2025-12-09 21:40:04 +00:00
3e4b480b95
fix: guided decoding params handling in vLLM ( #4770 )
...
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: Karen Chung <karenc@nvidia.com>
2025-12-09 01:10:35 +00:00
a8e5328ed8
ci: TRT-LLM multimodal CI ( #4118 )
...
Signed-off-by: Indrajit Bhosale <iamindrajitb@gmail.com>
2025-11-19 09:48:17 -08:00
381c428c11
refactor: change TensorRT-LLM metrics prefix from trtllm: to trtllm_ ( #4269 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-11-13 09:44:37 -08:00
49ecfe601f
fix: add prefill metrics support for SGLang disaggregated mode ( #3992 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-11-04 11:17:54 -08:00
bdef0ec566
test: add backend-specific metrics validation for E2E tests (part 1/3, vLLM only) ( #3804 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
2025-10-22 12:40:43 -07:00
d809906e62
feat: Add embedding support to sgl backend ( #3427 )
...
Signed-off-by: krishung5 <krish@nvidia.com>
2025-10-07 00:13:16 +00:00
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
ishandhanani