llama.cpp
ggml: WebGPU backend host improvements and style fixing
#14978

Merged

Commits

Add paramater buffer pool, batching of submissions, refactor command building/submission

reeselevine committed 222 days ago
Add header for linux builds

reeselevine committed 222 days ago
Free staged parameter buffers at once

reeselevine committed 222 days ago
Format with clang-format

reeselevine committed 222 days ago
Fix thread-safe implementation

reeselevine committed 221 days ago
Use device implicit synchronization

reeselevine committed 221 days ago
Merge remote-tracking branch 'upstream/master' into fixes

reeselevine committed 221 days ago
Update workflow to use custom release

reeselevine committed 221 days ago
Remove testing branch workflow

reeselevine committed 220 days ago