Tags: xek/llama.cpp
Tags
Add Conv2d for CPU (ggml-org#14388) * Conv2D: Add CPU version * Half decent * Tiled approach for F32 * remove file * Fix tests * Support F16 operations * add assert about size * Review: further formatting fixes, add assert and use CPU version of fp32->fp16
metal : disable fast-math for some cpy kernels (ggml-org#14460) * metal : disable fast-math for some cpy kernels ggml-ci * cont : disable for q4_1 ggml-ci * cont : disable for iq4_nl ggml-ci
cmake : Remove redundant include path in CMakeLists.txt (ggml-org#14452) * Update docker.yml 修改docker.yml文件中的内容使其停止周期性的运行该workflow，如果想要运行该workflow可以手动启动 * Remove redundant include path in CMakeLists.txt The parent directory '..' was removed from the include directories for the ggml-cpu-feats target, to avoid unnecessary include paths. * Enable scheduled Docker image builds Uncomments the workflow schedule to trigger daily Docker image rebuilds at 04:12 UTC, improving automation and keeping images up to date.
server : support jinja extra template kwargs (Qwen3 enable_thinking f… …eature), from command line and from client (ggml-org#13196) * initial commit for handling extra template kwargs * enable_thinking and assistant prefill cannot be enabled at the same time * can set chat_template_kwargs in command line * added doc * fixed formatting * add support for extra context in generic template init * coding standard: common/chat.cpp Co-authored-by: Georgi Gerganov <[email protected]> * coding standard: common/chat.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Apply suggestions from code review coding standard: cosmetic changes Co-authored-by: Georgi Gerganov <[email protected]> * fix merge conflict * chat.cpp: simplify calls to apply to ensure systematic propagation of extra_context (+ the odd existing additional_context) * normalize environment variable name * simplify code * prefill cannot be used with thinking models * compatibility with the new reasoning-budget parameter * fix prefill for non thinking models --------- Co-authored-by: Georgi Gerganov <[email protected]> Co-authored-by: Olivier Chafik <[email protected]>
SYCL: disable faulty fp16 exp kernel (ggml-org#14395) * SYCL: disable faulty fp16 CPU exponent for now * Revert "SYCL: disable faulty fp16 CPU exponent for now" This reverts commit ed0aab1. * SYCL: disable faulty fp16 CPU exponent for now * Fix logic of disabling exponent kernel
ggml : fix unmerged GGML_FPxx_TO_FPxx refactoring (ggml-org#14443)
vulkan: Add fusion support for RMS_NORM+MUL (ggml-org#14366) * vulkan: Add fusion support for RMS_NORM+MUL - Add a use_count to ggml_tensor, so we can detect if an output is used more than once. - Change the ggml-vulkan rms_norm shader to optionally multiply by another tensor. - Add detection logic and basic fusion logic in ggml-vulkan. - Add some testing support for fusion. Rather than computing one node at a time, allow for computing the whole graph and just testing one node's results. Add rms_norm_mul tests and enable a llama test. * extract some common fusion logic * fix -Winconsistent-missing-override * move ggml_can_fuse to a common function * build fix * C and C++ versions of can_fuse * move use count to the graph to avoid data races and double increments when used in multiple threads * use hash table lookup to find node index * change use_counts to be indexed by hash table slot * minimize hash lookups style fixes * last node doesn't need single use. fix type. handle mul operands being swapped. * remove redundant parameter --------- Co-authored-by: slaren <[email protected]>
CUDA: add bf16 and f32 support to cublas_mul_mat_batched (ggml-org#14361 ) * CUDA: add bf16 and f32 support to cublas_mul_mat_batched * Review: add type traits and make function more generic * Review: make check more explicit, add back comments, and fix formatting * Review: fix formatting, remove useless type conversion, fix naming for bools
PreviousNext