llama.cpp
ggml webgpu: profiling, CI updates, reworking of command submission
#16452
Merged
Merged
ggml webgpu: profiling, CI updates, reworking of command submission #16452
reeselevine
merged
16 commits into
ggml-org:master
from
reeselevine:master
Add profiling
5ae936a3
More detailed profiling
bd3d0807
Rework command submission to avoid global locks
400a58df
Update wait handling
ca43faa1
try new method of waiting on futures
98d98a2a
Add serializing of command submission in some cases
26c44f8e
Add new pool for timestamp queries and clean up logging
eabab9e0
Serialize command submission in CI and leave a TODO note
c30b22e2
Merge remote-tracking branch 'upstream/master'
168dd72d
Update webgpu CI
b926b0c5
CISC
approved these changes
on 2025-10-07
Add myself as WebGPU codeowner
d501ef4e
Deadlock avoidance
d56e0613
Leave WebGPU/Vulkan CI serialized
bcf8d9bd
Fix divide by 0
8a848cb0
CISC
commented
on 2025-10-07
CISC
commented
on 2025-10-07
CISC
commented
on 2025-10-07
Fix logic in division by inflight_threads
d3c7ddd4
Update CODEOWNERS and remove serialize submit option
a5e26c2d
Login to write a write a comment.
Login via GitHub