Georgi Gerganov 271191906c metal : enable FA for MLA heads (#18950)

2026-01-20 12:21:28 +02:00

..

CMakeLists.txt

ggml-metal: do not copy headers for embedded, use current binary dir for embedded (#18705)

2026-01-14 09:22:25 +02:00

ggml-metal-common.cpp

metal : fix loop bound in ggml_mem_ranges (#16412)

2025-10-03 19:18:56 +03:00

ggml-metal-common.h

metal : refactor + optimize v2 (#15995)

2025-09-17 20:38:12 +03:00

ggml-metal-context.h

metal : refactor + optimize v2 (#15995)

2025-09-17 20:38:12 +03:00

ggml-metal-context.m

metal : add residency sets keep-alive heartbeat (#17766)

2025-12-05 19:38:54 +02:00

ggml-metal-device.cpp

ggml : extend ggml_pool_1d + metal (#16429)

2026-01-16 16:59:56 +02:00

ggml-metal-device.h

ggml : extend ggml_pool_1d + metal (#16429)

2026-01-16 16:59:56 +02:00

ggml-metal-device.m

metal : enable FA for MLA heads (#18950)

2026-01-20 12:21:28 +02:00

ggml-metal-impl.h

ggml : extend ggml_pool_1d + metal (#16429)

2026-01-16 16:59:56 +02:00

ggml-metal-ops.cpp

metal : enable FA for MLA heads (#18950)

2026-01-20 12:21:28 +02:00

ggml-metal-ops.h

ggml : extend ggml_pool_1d + metal (#16429)

2026-01-16 16:59:56 +02:00

ggml-metal.cpp

ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH (#18535)

2026-01-08 11:03:21 +02:00

ggml-metal.metal

metal : enable FA for MLA heads (#18950)

2026-01-20 12:21:28 +02:00