public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
whisper.cpp/ggml/src/ggml-metal
History
Jeremy Demeule b90ec07aba metal: use shared buffers on eGPU (llama/17866) 
* metal: use shared buffers on eGPU

With #15906, I noticed on important regression when using metal backend on eGPU.
This commit restore the previous behavior and add an option to force its activation.

* metal: use shared buffers on eGPU

* metal: use shared buffers on eGPU
 		2025-12-18 08:20:56 +02:00
..
CMakeLists.txt metal : refactor + optimize v2 (llama/15995) 2025-09-20 13:46:10 +03:00
ggml-metal-common.cpp metal : fix loop bound in ggml_mem_ranges (llama/16412) 2025-10-12 11:16:23 +03:00
ggml-metal-common.h metal : refactor + optimize v2 (llama/15995) 2025-09-20 13:46:10 +03:00
ggml-metal-context.h metal : refactor + optimize v2 (llama/15995) 2025-09-20 13:46:10 +03:00
ggml-metal-context.m metal : add residency sets keep-alive heartbeat (llama/17766) 2025-12-12 17:53:18 +02:00
ggml-metal-device.cpp metal: SSM kernel improvements (llama/17876) 2025-12-12 17:53:23 +02:00
ggml-metal-device.h metal: SSM kernel improvements (llama/17876) 2025-12-12 17:53:23 +02:00
ggml-metal-device.m metal: use shared buffers on eGPU (llama/17866) 2025-12-18 08:20:56 +02:00
ggml-metal-impl.h metal: SSM kernel improvements (llama/17876) 2025-12-12 17:53:23 +02:00
ggml-metal-ops.cpp metal: SSM kernel improvements (llama/17876) 2025-12-12 17:53:23 +02:00
ggml-metal-ops.h metal: TRI, FILL, EXPM1, SOFTPLUS (llama/16623) 2025-12-12 17:53:17 +02:00
ggml-metal.cpp ggml : add ggml_top_k (llama/17365) 2025-12-12 17:53:08 +02:00
ggml-metal.metal metal: SSM kernel improvements (llama/17876) 2025-12-12 17:53:23 +02:00