| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
fix(litellm): preserve tool-free Responses requests (#816) Update the LiteLLM example and NeMo Gym runner from 1.97.0 to 1.102.0 so tool-free Responses requests do not acquire an empty `tools` array during translation to Chat Completions. With the previous pin, a request that omits `tools` is translated into a Chat request containing `tools: []`. Backends that reject empty tool arrays then fail before inference, including in the Gym tutorial. This is a dependency compatibility issue, not a routing decision failure. LiteLLM's upstream [fix](https://github.com/BerriAI/litellm/commit/4ea5749642de69e86e9414b1557eb8d00660c63c) removes both `tools` and `tool_choice` when there are no tools. The selected 1.102.0 version includes that behavior; Signed-off-by: Shawn Wang <32839114+enwaiax@users.noreply.github.com> | 4 天前 | |
docs(rust): repair libsy and protocol references (#263) * docs(rust): repair libsy and protocol references Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(libsy): list all public algorithms Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(libsy): make quickstart directly runnable Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(rust): streamline crate landing pages Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(libsy): focus the crate landing page Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(protocol): construct the simple request directly Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(rust): use readmes as crate documentation Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(libsy): run classifier in quick start Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(libsy): clarify crate purpose Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(rust): link crate landing page APIs Signed-off-by: nachiketb <nachiketb@nvidia.com> * docs(rust): complete API contract audit Signed-off-by: nachiketb <nachiketb@nvidia.com> --------- Signed-off-by: nachiketb <nachiketb@nvidia.com> | 1 个月前 | |
feat(libsy): Algorithms select a `Category` (e.g. "efficient") not a specific model. (#630) Instead of giving the available models to the algorithm in new we pass them alongside the request in run_stream where they go in the Driver. Algorithms work with Category instead of ModelId. Later libsy selects a model from the list for that category. The mapping from Category to ModelId lives in the Driver. See #588 for the originating idea. Assisted-by: Codex:GPT 5.6 Sol high Assisted-by: Claude:Opus 5 medium Reviewed-by: Claude:Opus 5 medium Signed-off-by: Graham King grahamk@nvidia.com | 15 天前 | |
Initial commit | 2 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 4 天前 | ||
| 1 个月前 | ||
| 15 天前 | ||
| 2 个月前 |