-
Notifications
You must be signed in to change notification settings - Fork 328
All issues
Issue creation is restricted in this repository
- #75 · leofang opened
on Jul 16, 2024 2 - #105 · leofang opened
on Sep 12, 2024 1 - #476 · spec-benno opened
on Feb 27, 2025 11
Issues
is:issue state:open
is:issue state:open
Search results
cuda.core: VirtualMemoryResourceOptions accepts values the driver rejects, and modify_allocation mishandles edge inputs
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Open.#2910 In NVIDIA/cuda-python;cuda.core: VirtualMemoryResource.modify_allocation(config=...) changes the resource's policy
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Open.#2909 In NVIDIA/cuda-python;cuda.core: a second grow of a grown VMM buffer fails
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Open.#2908 In NVIDIA/cuda-python;cuda.core: grown VMM buffers record the requested size, not the aligned size
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Open.#2907 In NVIDIA/cuda-python;EPIC: VirtualMemoryResource ownership redesign
cuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleEPICSoul of a releaseSoul of a releaseP1Medium priority - Should doMedium priority - Should doStatus: Open.Experiment with turning on annotation_typing globally
triageNeeds the team's attentionNeeds the team's attentionStatus: Open.cuda.core: a fast-path VMM grow leaves its extension unfreeable
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Open.#2887 In NVIDIA/cuda-python;cuda.core: VirtualMemoryResource.deallocate() unmaps without ordering on the stream
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Open.#2886 In NVIDIA/cuda-python;cuda.core: VirtualMemoryResource grow path's Buffer._clear() re-triggers mr.deallocate() on an already-freed VA range
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleStatus: Open.#2877 In NVIDIA/cuda-python;Drive PR #2266 (Migrating cuda-python sample codes from cuda-samples repository and Testing) across the finish line
triageNeeds the team's attentionNeeds the team's attentionStatus: Open.[FEA]: Make pixi lockfile freshness check mandatory
CI/CDCI/CD infrastructureCI/CD infrastructuretriageNeeds the team's attentionNeeds the team's attentionStatus: Open.#2850 In NVIDIA/cuda-python;cuda.core: DeviceMemoryResource setup is refused under non-relaxed stream capture, and tearing down the invalidated GraphBuilder segfaults
bugSomething isn't workingSomething isn't workingcuda.coreEverything related to the cuda.core moduleEverything related to the cuda.core moduleP1Medium priority - Should doMedium priority - Should doStatus: Open.