mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
[https://nvbugs/5629887][fix] Add missing device count guard for DSv32 multiGPU tests (#9159)
auto-close-inactive-issues.yml #4743:Scheduled
[None][fix] Fix KV cache manager test warnings (#9103)
auto-close-inactive-issues.yml #4742:Scheduled
[TRTLLM-9175][test] ensure sampling is async (#9076)
auto-close-inactive-issues.yml #4741:Scheduled
[None][fix] Display the GPU memory information in GiB unit. (#9070)
auto-close-inactive-issues.yml #4740:Scheduled
[None][fix] Improve type annotations on ResourceManager.get_resource_manager (#9013)
auto-close-inactive-issues.yml #4739:Scheduled
[None][infra] Waive failed tests for main 11/07 (#9008)
auto-close-inactive-issues.yml #4738:Scheduled
[None][infra] Update allowed list 2025.11.06 (#8987)
auto-close-inactive-issues.yml #4737:Scheduled
[https://nvbugs/5629790][chore] unwaive test. (#8967)
auto-close-inactive-issues.yml #4736:Scheduled
[https://nvbugs/5630345] [chore] skip deepseek-v3.2 fp8 kv tests on pre-Blackwell architectures (#8973)
auto-close-inactive-issues.yml #4735:Scheduled
[https://nvbugs/5630345][chore] unwaive DS-v32 nvfp4 and fp8 tests (#8887)
auto-close-inactive-issues.yml #4734:Scheduled
[https://nvbugs/5596343] [test] Waive flaky GPT-OSS cases (#8904)
auto-close-inactive-issues.yml #4733:Scheduled
[None][infra] Waive the failed test for main on 11/3 (#8875)
auto-close-inactive-issues.yml #4732:Scheduled
[#8781][fix] Cache the AllReduce wrapper to avoid re-allocating workspace which caused a hang (#8803)
auto-close-inactive-issues.yml #4731:Scheduled
[None][feat] Use ruff for formatting and linting new files by default (#8629)
auto-close-inactive-issues.yml #4730:Scheduled
[https://nvbugs/5474119][fix] Re-enable test (#8809)
auto-close-inactive-issues.yml #4729:Scheduled
[None][fix] Layer wise benchmarks: use local models, lint (#8799)
auto-close-inactive-issues.yml #4728:Scheduled
[TRTLLM-8976][feat] Move indexer-k-cache to KVCacheManager (#8699)
auto-close-inactive-issues.yml #4727:Scheduled
[None][fix] Properly raise error for nemotron H models (#8697)
auto-close-inactive-issues.yml #4726:Scheduled
[TRTLLM-8832][feat] fully async _select_generated_logits with tests (#8628)
auto-close-inactive-issues.yml #4725:Scheduled
[None][infra] Waive failed case on main 10/26 (#8668)
auto-close-inactive-issues.yml #4724:Scheduled
[TRTLLM-8238][feat] Add EVS support for nano-v2-vlm (#8024)
auto-close-inactive-issues.yml #4723:Scheduled
[None][feat] Pass KvCacheRetentionConfig to torch LlmRequest (#8634)
auto-close-inactive-issues.yml #4722:Scheduled
[TRTLLM-8714][fix] update create_input_processor to handle custom checkpoint format (#7811)
auto-close-inactive-issues.yml #4721:Scheduled
[None][fix] fixed cached model path in test (#8549)
auto-close-inactive-issues.yml #4720:Scheduled
[None][doc] Facilitates the integration of the transfer agent (#7867)
auto-close-inactive-issues.yml #4719:Scheduled
[https://nvbugs/5492250][fix] Remove isolated cases and unwaive cases (#8492)
auto-close-inactive-issues.yml #4718:Scheduled
[TRTLLM-7964][infra] Set nixl to default cache transceiver backend (#7926)
auto-close-inactive-issues.yml #4717:Scheduled
[None][feat] AutoDeploy: chunked prefill support (#8158)
auto-close-inactive-issues.yml #4716:Scheduled
[TRTLLM-8201][feat] Topological graph helpers (#8457)
auto-close-inactive-issues.yml #4715:Scheduled
[None][bug] Set NCCL_GRAPH_REGISTER to false to avoid hang (#8413)
auto-close-inactive-issues.yml #4714:Scheduled