Aman GuptaandGitHub b94050e896 CUDA: use LRU based eviction for cuda graphs (#21611) ...

* CUDA: use a ring-buffer for cuda graphs

* bump limit to 128

* use LRU eviction

* better naming

* do periodic clean-up

2026-04-17 23:24:21 +08:00

..

ggml-blas

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-cann

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-cpu

ggml-cpu: add 128-bit RVV implementation for Quantization Vector Dot (#20633)

2026-04-16 11:15:15 +03:00

ggml-cuda

CUDA: use LRU based eviction for cuda graphs (#21611)

2026-04-17 23:24:21 +08:00

ggml-hexagon

hexagon: optimize HMX matmul operations (#21071)

2026-04-16 13:48:34 -07:00

ggml-hip

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-metal

metal: Implement ROLL op (#21946)

2026-04-16 11:54:37 +03:00

ggml-musa

ggml-cuda: native bf16 flash attention for vec kernel (#20525)

2026-03-22 11:05:51 +01:00

ggml-opencl

opencl: refactor q8_0 set_tensor and mul_mat host side dispatch for Adreno (#21938)

2026-04-16 22:28:33 -07:00

ggml-openvino

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-rpc

rpc : add native RDMA transport for RPC backend (RoCEv2) (#20590)

2026-04-15 16:44:02 +03:00

ggml-sycl

[SYCL] Fix Q8_0 reorder: garbage on 2nd prompt + crash on full VRAM (#21638)

2026-04-16 08:34:05 +03:00

ggml-virtgpu

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-vulkan

vulkan: optimize im2col (#21713)

2026-04-15 19:04:51 +02:00

ggml-webgpu

ggml-webgpu: compute pass batching and removing profiling overhead (#21873)

2026-04-16 11:12:19 +03:00

ggml-zdnn

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-zendnn

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

CMakeLists.txt

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-alloc.c

ggml : remove ggml-ext.h (#21869)

2026-04-14 17:32:58 +03:00

ggml-backend-dl.cpp

hexagon: enable offloading to Hexagon on Windows on Snapdragon (#19150)

2026-01-29 12:33:21 -08:00

ggml-backend-dl.h

hexagon: enable offloading to Hexagon on Windows on Snapdragon (#19150)

2026-01-29 12:33:21 -08:00

ggml-backend-impl.h

ggml: backend-agnostic tensor parallelism (experimental) (#19378)

2026-04-09 16:42:19 +02:00

ggml-backend-meta.cpp

CUDA: manage NCCL communicators in context (#21891)

2026-04-15 15:58:40 +02:00

ggml-backend-reg.cpp

ggml : add OpenVINO backend (#15307)

2026-03-14 07:56:55 +02:00

ggml-backend.cpp

ggml: add graph_reused (#21764)

2026-04-16 17:21:28 +08:00

ggml-common.h

ggml: add Q1_0 1-bit quantization support (CPU) (#21273)

2026-04-06 20:55:21 +02:00

ggml-impl.h

ggml: add graph_reused (#21764)

2026-04-16 17:21:28 +08:00

ggml-opt.cpp

fix: free ctx_copy in ggml_opt_free to plug per-training-session leak (#21592)

2026-04-08 17:40:15 +02:00

ggml-quants.c

ggml: add Q1_0 1-bit quantization support (CPU) (#21273)

2026-04-06 20:55:21 +02:00

ggml-quants.h

ggml: add Q1_0 1-bit quantization support (CPU) (#21273)

2026-04-06 20:55:21 +02:00

ggml-threading.cpp

ggml : build backends as libraries (#10256)

2024-11-14 18:04:35 +01:00

ggml-threading.h

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)

2024-12-12 19:02:49 +01:00

ggml.c

ggml: add graph_reused (#21764)

2026-04-16 17:21:28 +08:00

ggml.cpp

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)

2025-06-01 13:43:57 +03:00

gguf.cpp

llama: fix llama-model-saver (#20503)

2026-03-25 12:53:16 +02:00