leonardHONGandGeorgi Gerganov b13deaabae ggml-cuda: flush legacy pool on OOM and retry (llama/22155) ...

* ggml-cuda: flush legacy pool on OOM and retry

Signed-off-by: 梁厚宏 <2695316095@qq.com>

* Address review comments: add explicit sync, update destructor, clean up MUSA macros

Signed-off-by: 梁厚宏 <2695316095@qq.com>

---------

Signed-off-by: 梁厚宏 <2695316095@qq.com>

2026-04-30 11:29:14 +03:00

..

ggml-blas

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-cann

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-cpu

ggml-cpu: Optimized x86 and generic cpu q1_0 dot (follow up) (llama/21636)

2026-04-30 11:29:14 +03:00

ggml-cuda

ggml-cuda: flush legacy pool on OOM and retry (llama/22155)

2026-04-30 11:29:14 +03:00

ggml-hexagon

hexagon: optimize HMX matmul operations (llama/21071)

2026-04-30 11:29:11 +03:00

ggml-hip

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-metal

metal: Implement ROLL op (llama/21946)

2026-04-30 11:29:11 +03:00

ggml-musa

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

2026-03-29 15:04:36 +03:00

ggml-opencl

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

2026-04-30 11:29:12 +03:00

ggml-openvino

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-rpc

rpc : refactor the RPC transport (llama/21998)

2026-04-30 11:29:12 +03:00

ggml-sycl

Fix reorder MMVQ assert on unaligned vocab sizes (llama/22035)

2026-04-30 11:29:13 +03:00

ggml-virtgpu

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-vulkan

vulkan: optimize im2col (llama/21713)

2026-04-30 11:29:10 +03:00

ggml-webgpu

ggml-webgpu: updated matrix-vector multiplication (llama/21738)

2026-04-30 11:29:13 +03:00

ggml-zdnn

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-zendnn

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

CMakeLists.txt

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-alloc.c

ggml : remove ggml-ext.h (llama/21869)

2026-04-30 11:29:09 +03:00

ggml-backend-dl.cpp

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

2026-01-30 15:56:40 +02:00

ggml-backend-dl.h

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

2026-01-30 15:56:40 +02:00

ggml-backend-impl.h

ggml: backend-agnostic tensor parallelism (experimental) (llama/19378)

2026-04-30 11:29:05 +03:00

ggml-backend-meta.cpp

Tensor-parallel: Fix delayed AllReduce on Gemma-4 MoE (llama/22129)

2026-04-30 11:29:14 +03:00

ggml-backend-reg.cpp

ggml : add OpenVINO backend (llama/15307)

2026-03-16 13:10:15 +02:00

ggml-backend.cpp

ggml: add graph_reused (llama/21764)

2026-04-30 11:29:11 +03:00

ggml-common.h

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

2026-04-30 11:29:01 +03:00

ggml-impl.h

ggml: add graph_reused (llama/21764)

2026-04-30 11:29:11 +03:00

ggml-opt.cpp

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

2026-04-30 11:29:03 +03:00

ggml-quants.c

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

2026-04-30 11:29:01 +03:00

ggml-quants.h

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

2026-04-30 11:29:01 +03:00

ggml-threading.cpp

ggml : build backends as libraries (llama/10256)

2024-11-20 21:00:08 +02:00

ggml-threading.h

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797)

2024-12-18 12:52:16 +02:00

ggml.c

ggml: add graph_reused (llama/21764)

2026-04-30 11:29:11 +03:00

ggml.cpp

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

2025-05-29 09:56:26 +03:00

gguf.cpp

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

2026-03-29 15:04:36 +03:00