Georgi Gerganov 4a84b0ad10 metal : add TQ2_0 support (#26980) ...

* metal: add TQ2_0 support

Add support for the GGML_TYPE_TQ2_0 (ternary, 2 bits per element) type in
the Metal backend.

Assisted-by: llama.cpp:DeepSeek-v4-Flash-0731

* cont : optimize mul_mv kernel

- float ops over integer ops
- precalculate sums
- hoist coef out of the inner loop
- contiguous y loads

llama.cpp:DeepSeek-v4-Flash-0731

2026-08-13 14:33:53 +03:00

..

ggml-blas

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-cann

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-cpu

ggml-cpu/ops: vectorize flash-attention V-cache F16 to F32 conversion (#26947)

2026-08-13 12:04:46 +03:00

ggml-cuda

CUDA: only disable CUDA graphs when mul_mat_id actually needs a stream sync (#26802)

2026-08-11 20:50:03 +03:00

ggml-et

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-hexagon

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-hip

ggml-hip : remove -funsafe-math-optimizations (#26696)

2026-08-13 08:38:02 +02:00

ggml-metal

metal : add TQ2_0 support (#26980)

2026-08-13 14:33:53 +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: default FA c8 cluster width to 16 on X1E (#26433)

2026-08-11 23:10:27 -07:00

ggml-openvino

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-rpc

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-sycl

sycl: remove separate fp32 type promotion in gemm non-oneDNN path (#26372)

2026-08-13 12:02:18 +03:00

ggml-virtgpu

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-vulkan

vulkan: add TQ2_0 (ternary) support (#25850)

2026-08-12 08:07:23 +03:00

ggml-webgpu

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-zdnn

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-zendnn

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

CMakeLists.txt

ggml: enable PowerPC backend variants on AIX (#25983)

2026-07-22 17:26:40 +08:00

ggml-alloc.c

ggml-alloc: fix out-of-bounds read in ggml_dyn_tallocr_remove_block (ggml/1492)

2026-05-25 12:38:01 +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

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

ggml-backend-reg.cpp

ggml-et: Initial ET backend (#24179)

2026-07-10 12:38:34 +08:00

ggml-backend.cpp

ggml: use dynamic allocation for split graph inputs (#22789)

2026-08-03 18:03:14 +03:00

ggml-common.h

Add Q2_0 quantization: type definition and CPU backend (#24448)

2026-07-07 12:05:47 -07:00

ggml-feats.h

ggml : fix arm builds, unused var (#26991)

2026-08-13 07:57:24 +03:00

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

Add Q2_0 quantization: type definition and CPU backend (#24448)

2026-07-07 12:05:47 -07:00

ggml-quants.h

Add Q2_0 quantization: type definition and CPU backend (#24448)

2026-07-07 12:05:47 -07:00

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

mtmd/ggml: add ggml_build_forward_order (#26649)

2026-08-06 00:47:59 +02:00

ggml.cpp

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

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

gguf.cpp

gguf : harden loader against malformed tensor dims and metadata types (#25596)

2026-08-12 15:07:48 +03:00