| .. |
|
cmake
|
…
|
|
|
ggml-cann
|
Chores : Typos fixing round 3 (project wide, ggml dir included, comments and user facing msg only) (#2249)
|
2026-08-04 07:15:28 +03:00 |
|
ggml-cuda
|
cuda: chunked WY delta-net kernel v1 (opt-in DELTA_WY_CUDA=1) + harness --cuda mode
|
2026-09-05 21:13:04 -03:00 |
|
ggml-sycl
|
…
|
|
|
iqk
|
qwen4exp: PP/TG opts for Ampere+Zen3 (merged experts, fused PLE taps, Zen3 tiling)
|
2026-09-05 20:14:29 -03:00 |
|
llamafile
|
…
|
|
|
vulkan-shaders
|
vulkan : add IQ4_KS and IQ4_KT support (#2332)
|
2026-08-24 18:20:35 +02:00 |
|
CMakeLists.txt
|
cuda : repair the HIP build, and validate IQ4_KS and IQ4_KT on RDNA3 (#2339)
|
2026-08-25 08:50:44 +02:00 |
|
ggml-aarch64.c
|
…
|
|
|
ggml-aarch64.h
|
…
|
|
|
ggml-alloc.c
|
Support for Qwen 3.5 MTP (dense models only) (#1698)
|
2026-04-28 07:47:50 +02:00 |
|
ggml-backend-impl.h
|
…
|
|
|
ggml-backend.cpp
|
CUDA graphs improvements (#2316)
|
2026-08-24 09:51:59 +02:00 |
|
ggml-cann.cpp
|
…
|
|
|
ggml-common.h
|
MXFP4_R8 (#2196)
|
2026-07-28 08:03:59 +03:00 |
|
ggml-cuda.cu
|
qwen4exp: MTP (NextN) self-speculative decoding support (#2369)
|
2026-09-02 18:49:42 +02:00 |
|
ggml-impl.h
|
Do not include ggml-impl.h in ggml-cuda.cu (#2264)
|
2026-08-07 07:23:43 +03:00 |
|
ggml-metal.m
|
metal: initialize encode_async in ggml_backend_metal_init (#2334)
|
2026-08-26 17:15:46 +02:00 |
|
ggml-metal.metal
|
metal: implement ROPE_MULTI (mrope/imrope) kernels (#2140)
|
2026-07-17 17:49:13 +03:00 |
|
ggml-moe-prefetch.cpp
|
Add --prefetch-experts to stream mmap'd MoE experts into page cache (#2101)
|
2026-07-11 10:43:42 +03:00 |
|
ggml-moe-prefetch.h
|
Add --prefetch-experts to stream mmap'd MoE experts into page cache (#2101)
|
2026-07-11 10:43:42 +03:00 |
|
ggml-quants.c
|
Quantization fudge factors (#2361)
|
2026-08-27 17:35:04 +02:00 |
|
ggml-quants.h
|
Quantization options (#1677)
|
2026-04-23 09:05:39 +02:00 |
|
ggml-rpc.cpp
|
rpc: fix crash running GLM-5.2 (glm-dsa) split over RPC (#2360)
|
2026-08-26 17:02:43 +02:00 |
|
ggml-sycl.cpp
|
Chores : Typos fixing round 3 (project wide, ggml dir included, comments and user facing msg only) (#2249)
|
2026-08-04 07:15:28 +03:00 |
|
ggml-utils.h
|
Do not include ggml-impl.h in ggml-cuda.cu (#2264)
|
2026-08-07 07:23:43 +03:00 |
|
ggml-vulkan.cpp
|
vulkan : add IQ4_KS and IQ4_KT support (#2332)
|
2026-08-24 18:20:35 +02:00 |
|
ggml.c
|
qwen4exp: PP/TG opts for Ampere+Zen3 (merged experts, fused PLE taps, Zen3 tiling)
|
2026-09-05 20:14:29 -03:00 |
Marvin
a34feeb0f9