nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ik_llama_opt/ggml/src
History
Kawrakow 7642ac3eca
Fix massive inefficiency in CUDA Q->f32/f16 and f32/f16->Q copies (#2279) 
* CUDA indexer topk: this is better for PP

* Don't overstep

* Cleanup

* Allow Q8_0 cache in the CUDA DSA implementation

* DS4: do not cast caches to f32

* Fix massive inefficiency in CUDA Q->f32/f16 and f32/f16->Q copies

* Re-enable -ictk | --indexer-cache-type-k
 		2026-08-08 17:26:59 +03:00
..
cmake Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
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 Fix massive inefficiency in CUDA Q->f32/f16 and f32/f16->Q copies (#2279) 2026-08-08 17:26:59 +03:00
ggml-sycl Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
iqk Another minor indexer optimization on the CPU (#2231) 2026-08-05 08:15:41 +03:00
llamafile
…
vulkan-shaders Port of Qwen3-VL support from mainline (#883) 2025-11-04 19:20:54 +02:00
CMakeLists.txt Do not include ggml-impl.h in ggml-cuda.cu (#2264) 2026-08-07 07:23:43 +03:00
ggml-aarch64.c Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00
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 Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
ggml-backend.cpp DS4 optimizations (part 2) (#2179) 2026-07-26 16:03:56 +03:00
ggml-cann.cpp Merge vulkan code from mainline up to commit of 6/28/2025 (#563) 2025-07-02 08:49:42 +02:00
ggml-common.h MXFP4_R8 (#2196) 2026-07-28 08:03:59 +03:00
ggml-cuda.cu Do not include ggml-impl.h in ggml-cuda.cu (#2264) 2026-08-07 07:23:43 +03:00
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: implement ROPE_MULTI (mrope/imrope) kernels (#2140) 2026-07-17 17:49:13 +03:00
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 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-quants.h Quantization options (#1677) 2026-04-23 09:05:39 +02:00
ggml-rpc.cpp server: improve speed of speculative decoding (#1119) 2026-01-10 08:01:22 +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 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.c Do not include ggml-impl.h in ggml-cuda.cu (#2264) 2026-08-07 07:23:43 +03:00