main

GGitHubdocs(benchmark): add Jev routing profile and README results (#1007)

4cbb2d11创建于 3 天前历史提交

文件	最后提交记录	最后更新时间
deepswe-v11-advisor-gate-luna-sol.toml	docs(benchmark): add DeepSWE v1.1 advisor-gate routing profile (#811) Signed-off-by: Zengyuan Liu <zengyuanl@nvidia.com>	27 天前
deepswe-v11-plan-execute-luna-sol.toml	docs(benchmark): add DeepSWE plan-execute profile (#824) * docs(benchmark): add DeepSWE plan-execute profile Signed-off-by: Ryan Lempka <rlempka@nvidia.com> * docs(benchmark): clarify standard pricing Signed-off-by: Ryan Lempka <rlempka@nvidia.com> --------- Signed-off-by: Ryan Lempka <rlempka@nvidia.com>	26 天前
deepswe-v11-stage-router-luna-sol.toml	docs(benchmark): add DeepSWE stage-router profile (#812) * docs(benchmark): add DeepSWE stage-router profile Signed-off-by: Sabhatina Selvam <sabhatinas@nvidia.com> * docs(benchmark): remove stage-profile reasoning override Signed-off-by: Sabhatina Selvam <sabhatinas@nvidia.com> --------- Signed-off-by: Sabhatina Selvam <sabhatinas@nvidia.com>	27 天前
tau2-telecom-custom-opus-qwen-aggressive.toml	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	1 个月前
tau2-telecom-custom-opus-qwen-balanced.toml	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	1 个月前
tb21-escalation-opus-glm-deepseek.toml	docs(benchmark): add v0.2.0 TB-2.1 escalation routing profile (#490) Signed-off-by: Lin Jia <linj@nvidia.com>	1 个月前
tb21-jev-opus-glm.toml	docs(benchmark): add Jev routing profile and README results (#1007) Signed-off-by: nachiketb <nachiketb@nvidia.com>	3 天前