Search: “openai”

1 results

Each lane shows up to 8 recent matching entries, ordered from earlier to later. Tracks load separately to keep the 75,000+ entry wiki fast.

Companies

CompanyOpenAI1 recent entries

4 Aug 2026v0.32.6

What's Changed Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically /v1/chat/completions streaming now matches OpenAI's wire format: rol