Skip to content

Pull requests: beehive-lab/TornadoVM

New pull request New
14 Open 669 Closed
14 Open 669 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[cuda] Propagate CUDA driver failures to Java instead of only logging them 6.0.0
#1025 opened Aug 5, 2026 by mikepapadim Member Loading…
4
[profiler] Harvest device timestamps after the stream drains instead of blocking on every operation (profiler-on cost -34%)
#1024 opened Aug 5, 2026 by mikepapadim Member Loading…
5
[cuda] Skip stream synchronisation when nothing has been enqueued since the last drain (3 syncs per execution to 1)
#1023 opened Aug 5, 2026 by mikepapadim Member Loading…
3
[cuda] Skip the per-launch kernel stack-frame upload when the device copy is unchanged (2.03x on short task graphs) CUDA enhancement New feature or request
#1022 opened Aug 5, 2026 by mikepapadim Member Loading…
3
Make --printBytecodes readable: verbosity modes, per-execution summaries and a Graphviz export
#1009 opened Jul 30, 2026 by mikepapadim Member Loading…
10
[cuda] Report rejected kernel launches and failed copies instead of only logging them CUDA
#988 opened Jul 26, 2026 by mikepapadim Member Loading…
2 of 7 tasks
1
Asynchronous execution: TornadoExecutionPlan.executeAsync() completed by a CUDA host callback
#986 opened Jul 26, 2026 by mikepapadim Member Loading…
2 of 7 tasks
1
CUDA stream usage: visible routing, DAG-based stream selection, plan-level tuning, examples and measurements CUDA
#982 opened Jul 25, 2026 by mikepapadim Member Loading…
2 of 7 tasks
@orionpapadakis
2
[showcase] LLM-inference benchmarks across the NVIDIA stack (CUDA backend + hybrid library tasks)
#953 opened Jul 20, 2026 by mikepapadim Member Loading…
2
[cuda] NCCL multi-GPU collectives: TornadoNccl API (allReduce/broadcast/reduce/allGather/reduceScatter) combined with task graphs CUDA
#920 opened Jul 11, 2026 by mikepapadim Member Loading…
11
[cuda] cuTENSOR hybrid-API provider: FP32 tensor contractions (einsum) as library tasks 6.0.0 CUDA
#913 opened Jul 11, 2026 by mikepapadim Member Loading…
12
Remove dependency to JVMCI for JDK27+ backwards compatiblity for JDKs 21-26 6.0.0
#894 opened Jul 4, 2026 by mikepapadim Member Loading…
@mikepapadim @stratika
141
[hybrid] CUDA-C backend: delegate @Reduce to CUB warp reductions CUDA enhancement New feature or request
#889 opened Jul 3, 2026 by mikepapadim Member Loading…
38
Support for JDK25.0.2 and migrate Graal compiler version to 25.0.2 graal-update Update the Graal JIT compiler jdk
#798 opened Feb 11, 2026 by mikepapadim Member • Draft
4 of 7 tasks
@mikepapadim
93
ProTip! Follow long discussions with comments:>50.