TRL

README を読み込み中

1. v1.14.12026-09-29Fix the server-mode crash at the first weight sync on vLLM 0.20 to 0.25
2. v1.14.02026-09-25> [!WARNING]
3. v1.13.02026-09-10A new long-context guide plus a runnable example that trains a book-length sequence per step on a single 8×H100 node.
4. v1.12.02026-08-26During the v1.11.0 release, VERSION was bumped to 1.12.0 instead of 1.12.0.dev0. Our publish workflow fires on any push…
5. v1.11.02026-08-26trl vllm-serve used to run a custom FastAPI app around vLLM's LLM, with its own data-parallel fan-out and a worker exte…