Brandon PelfreyandRoger Wang af16446bf3 Vram semaphore infra (#44465) ...

Signed-off-by: Brandon Pelfrey <bpelfrey@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

2026-06-26 17:32:51 -07:00

..

inputs

[Bugfix] Normalize malformed dict prompts that carry token IDs in prompt (#40339)

2026-04-21 07:44:36 +00:00

__init__.py

[Chore] Move BaseRenderer to base.py (#34308)

2026-02-11 00:29:51 -08:00

base.py

Vram semaphore infra (#44465)

2026-06-26 17:32:51 -07:00

deepseek_v4.py

[Feat] DeepSeek V4 Rebased (#40860)

2026-04-26 18:31:08 -07:00

deepseek_v32.py

[Bugfix] Offload blocking tokenizer ops to shared thread pool to unblock event loop (#34789)

2026-03-26 22:17:00 -07:00

embed_utils.py

feat: Enable prompt_embeds Content Part Support in vLLM Chat Completions API (#40720)

2026-05-01 10:05:55 +08:00

hf.py

[API] Add token offsets to render endpoints (/v1/.../render) (#44226)

2026-06-26 05:02:52 -07:00

mistral.py

[Bugfix] Offload blocking tokenizer ops to shared thread pool to unblock event loop (#34789)

2026-03-26 22:17:00 -07:00

online_derenderer.py

[Frontend] Split ServingRender into renderer and entrypoint. (#44285)

2026-06-23 11:19:09 +00:00

online_renderer.py

[Frontend] Split ServingRender into renderer and entrypoint. (#44285)

2026-06-23 11:19:09 +00:00

params.py

[API] Add token offsets to render endpoints (/v1/.../render) (#44226)

2026-06-26 05:02:52 -07:00

registry.py

Remove grok model arch from vllm (#46706)

2026-06-25 23:02:10 -07:00

terratorch.py

[Renderer] Consolidate factory methods (#38218)

2026-03-26 12:19:22 +00:00