yang rui 3dc895df4d

feat(models): pace shared RPM budgets before dispatch (#5432) ...

* feat(models): add shared RPM admission queues

* fix(models): address admission pacing review feedback

* docs: simplify request admission quick start guidance

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-09-15 07:14:35 +08:00

..

__init__.py

…

AGENTS.md

feat(models): pace shared RPM budgets before dispatch (#5432)

2026-09-15 07:14:35 +08:00

assistant_payload_replay.py

…

claude_provider.py

…

credential_loader.py

fix(models): reuse the Claude Code OAuth token read from a file descriptor (#5411)

2026-09-14 09:23:12 +08:00

factory.py

feat(models): pace shared RPM budgets before dispatch (#5432)

2026-09-15 07:14:35 +08:00

mindie_provider.py

fix(models): restore usage_metadata in MindIE tool-mode simulated streaming (#5195)

2026-09-05 14:10:18 +08:00

openai_codex_provider.py

…

patched_deepseek.py

…

patched_mimo.py

…

patched_minimax.py

…

patched_openai.py

…

patched_stepfun.py

…

request_admission.py

feat(models): pace shared RPM budgets before dispatch (#5432)

2026-09-15 07:14:35 +08:00

vllm_provider.py

…