LLM-Inference/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-08-12 22:31:22 +04:00
Code Issues Packages Projects Releases Wiki Activity
4,839 Commits 65 Branches 88 Tags
2ca53bb45e38748d07b310eeb36245a7157ac882
Commit Graph
9 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Winston MaandGeorgi Gerganov ae09736e83 vulkan: record actual memory properties during buffer creation (llama/24326) 2026-06-19 12:53:43 +03:00
Winston MaandGeorgi Gerganov 694579182f vulkan: prefer host-visible memory buffers on UMA devices (llama/22930) 
* implement UMA host-visible memory

* update based on 0cc4m's suggestion
 2026-06-19 12:53:43 +03:00
Winston MaandGeorgi Gerganov 6870cfd616 vulkan: add fast path for contiguous buffer transfers (llama/23973) 2026-06-15 10:33:53 +03:00
Winston MaandGeorgi Gerganov c471bcce1b vulkan: reduce host memory lock contention (llama/23376) 
* vulkan: reduces lock contention

* replace unique_lock with lock_guard
 2026-06-08 14:36:36 +03:00
Winston MaandGeorgi Gerganov aea93ada61 vulkan: Removed unused functions (llama/23175) 2026-06-08 14:36:36 +03:00
Winston MaandGeorgi Gerganov 816c3029bc vulkan: fix wrong index variable in inner loop (llama/23665) 2026-05-29 09:47:30 +03:00
Winston MaandGeorgi Gerganov 5db94bac04 vulkan: Fix memory logger unsafe iterator access (llama/23667) 2026-05-29 09:47:30 +03:00
Winston MaandGeorgi Gerganov 80e87ec453 vulkan: avoid preferring transfer queue on AMD UMA devices (llama/22455) 2026-05-29 09:47:30 +03:00
Winston MaandGeorgi Gerganov ef5ddecff9 vulkan: removed duplicate #include <memory> in headers (llama/23144) 2026-05-25 12:26:07 +03:00