whisper.cpp

Commit Graph

Author	SHA1	Message	Date
Aleksei Nikiforov	55927d42ef	ggml-zdnn : mark zDNN buffers as non-host (llama/18967) While buffers reside in host memory, additional transformation is needed to use buffers with zDNN. Fixes #18848	2026-01-30 15:56:40 +02:00
Georgi Gerganov	47f3e3b927	ggml : add ggml_build_forward_select (llama/18550) * ggml : add ggml_build_forward_select * cuda : adapt CUDA graph compat to new feature * vulkan : update logic to handle command buffer closing * ggml : check compute for fusion * ggml : add comment	2026-01-30 15:56:40 +02:00
Aaron Teo	c706a50746	zdnn: refactor codebase + add docs (llama/16178) * zdnn: initial matmul refactor Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: rm static from funcs Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: update ggml-zdnn.h Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: change header files to hpp Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: switch to common.hpp Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: move mulmat forward around Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: rm inline from utils Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: code cleanup Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: add zDNN docs Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> --------- Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>	2025-09-29 15:18:09 +03:00
Jeff Bolz	7fcb7e83ec	rename optimize_graph to graph_optimize (llama/16082)	2025-09-20 13:46:39 +03:00
Aaron Teo	7dca05ca77	ggml-zdnn: rm user mapped buffers (llama/15965) * ggml-zdnn: rm user mapped buffers Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: rm dead code Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * ggml-zdnn: attempt to fix missing extra data buffer free Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> --------- Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>	2025-09-20 13:45:29 +03:00
Aaron Teo	e902731ccc	ggml-zdnn: fix #15414 , activate FP16 and BF16 acceleration and incorrect zTensor free (llama/15839)	2025-09-20 13:45:28 +03:00
Jeff Bolz	c29cd54818	vulkan: sort graph to allow more parallel execution (llama/15850) * vulkan: sort graph to allow more parallel execution Add a backend proc to allow the backend to modify the graph. The vulkan implementation looks at which nodes depend on each other and greedily reorders them to group together nodes that don't depend on each other. It only reorders the nodes, doesn't change the contents of any of them. With #15489, this reduces the number of synchronizations needed. * call optimize_graph per-split	2025-09-20 13:42:52 +03:00
Aaron Teo	03d6607691	ggml : initial zDNN backend (llama/14975)	2025-08-18 20:30:45 +03:00

8 Commits