Comunidad Guías…

Ayuda y problemas de ai-helm

Pregunta a la comunidad o invita a KiBot con contexto del repositorio.

Publicar un problema

No publiques contraseñas, tokens ni claves privadas. HostingByte aplica una redacción básica de secretos evidentes antes de guardar el texto.

Problemas en HostingByte

Todavía no hay problemas publicados.

Issues abiertas upstream

#679 [Ticket]: Codex / ChatGPT custom-model-provider OAuth2 integration with our gateway · 2 comentarios #680 [Ticket]: Claude Code OAuth2 integration with our gateway · 1 comentarios #369 [Epic]: Track AIEG #2218 — remove the refero Content-Type workaround when fixed · 1 comentarios #1132 [Ticket]: Implement the Qwen3.5-2B --max-num-seqs sizing protocol (P1, epic #1103) · 2 comentarios #1126 [Ticket]: GPU fleet halved — hetzner-k8s-gpu-2 removed; one card, one model · 1 comentarios #1104 [Ticket]: P1 — raise --max-num-seqs and re-run the sweep (the knee is a config constant, not the GPU) · 2 comentarios #1106 [Ticket]: Documentation fact-check long tail — 8 documents with known-false claims · 0 comentarios #1105 [Ticket]: The 2026-08-25 direct-path benchmark measured 401s and reported a PASS — its numbers are void · 0 comentarios #1103 [Epic]: Drive the two-card fleet to a measured performance envelope · 2 comentarios #1102 [Ticket]: Spike — is an L2 disk tier the only way to a KV cache larger than APC? (gate on #4701 first) · 1 comentarios #1101 [Ticket]: In-place restart of the vLLM container always fails once — VRAM not yet released, error blames gpuMemoryUtilization · 1 comentarios