a9e0696023
fix(api): preserve interleaved reasoning order for KV cache correctness ( #6442 )
...
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
2026-02-24 02:20:54 +00:00
0e55e82128
fix: tool call validation and stop words. ( #5504 )
...
Signed-off-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com>
2026-02-14 01:21:10 +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
2cee89a05c
feat: support `reasoning_content` context management (DeepSeek v3.2 & GLM-4.7 & Kimi-2.5) ( #6107 )
...
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
2026-02-11 05:34:32 +00:00
9f76d0606c
feat: text to image vLLM Omni ( #5912 )
...
Signed-off-by: ayushag <ayushag@nvidia.com>
2026-02-09 18:19:27 -05:00
7e970d44c9
feat: image diffusion with SGLang diffusion ( #5609 )
...
Signed-off-by: Konrad Nowicki <knowicki@nvidia.com>
Co-authored-by: dagil-nvidia <dagil@nvidia.com>
2026-02-03 21:19:21 +00:00
6f9619a210
feat(vllm): Add prompt embeds support for pre-computed inference inputs ( #4739 )
...
Signed-off-by: Wenqi Glantz <wglantz@nvidia.com>
2026-01-08 20:03:10 +00:00
6bfb41dee4
feat: add continuous_usage_stats option for per-chunk usage ( #5139 )
...
Signed-off-by: Guan Luo <gluo@nvidia.com>
2026-01-03 12:56:44 -08:00
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
f63e273c43
feat: add auto-generated frontend OpenAPI spec and helper binary ( #4802 )
...
Signed-off-by: Satvik Matta <smatta@nvidia.com>
2025-12-22 21:45:03 +00:00
45e881d324
feat: Support for field include_stop_str_in_output ( #4924 )
...
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
2025-12-13 00:22:09 +00:00
263f99dc8b
feat: nvext field to OpenAI APIs and add worker_id reporting (vLLM) ( #4372 )
...
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
2025-11-19 06:05:10 +00:00
0f5dd2b780
feat: Add vLLM multimodal audio support ( #2760 )
...
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Signed-off-by: krishung5 <krish@nvidia.com>
Co-authored-by: Kris Hung <krish@nvidia.com>
2025-11-13 13:55:48 -08:00
b4c8d9481d
feat: echo parameter validation for `/v1/completions` ( #3813 )
...
Signed-off-by: Krishnan Prashanth <kprashanth@nvidia.com>
2025-10-27 20:20:01 +00:00
13156361fb
chore: relaxing constraints on metadata field, adding metadata field to completions API ( #3240 )
...
Signed-off-by: Nicholas Edelman <nedelman@nvidia.com>
2025-09-29 11:35:05 -05:00
435803ea16
chore: add additional param support for multimodal models ( #3042 )
...
Signed-off-by: Ryan Lempka <rlempka@nvidia.com>
2025-09-16 16:26:39 +00:00
78a1107441
feat: Add vLLM multimodal video support ( #2738 )
...
Signed-off-by: krishung5 <krish@nvidia.com>
2025-08-28 03:41:56 +00:00
bce7458842
chore: Rust to 1.89 and edition 2024 ( #2659 )
2025-08-22 16:17:15 -07:00
c12fe5011d
chore: remove flatten for chat response types, add reasoning_content ( #2543 )
...
Changing the chat completions response objects from structs to types of dynamo_async_openai
Implement aggregator traits for them chat completion structs
add reasoning_content under message and delta message in lib/async-openai
2025-08-20 00:51:36 +00:00
199b9a30f4
chore: Bring async-openai into repo as request starter ( #2520 )
...
Co-authored-by: Graham King <grahamk@nvidia.com>
2025-08-19 17:47:01 -04:00
MatejKosec