* adds simple llama grammar tests
* fix lint and add Makefile
* 0 terminate code_points
* avoid dangling pointers in candidate cleanup
* cleanup grammar at end of test
The GGML memory allocator consistently places a tensor within the
optimal-fit memory block, which is the smallest block capable of
accommodating the tensor's size. During the measurement phase, the final
block is generously sized, ensuring it never qualifies as the
optimal-fit block as long as there exists another block capable of
accommodating the tensor. Nevertheless, in the evaluation phase, the
last block is constrained in size and could potentially qualify as the
optimal-fit block. Consequently, there exists the possibility of a
tensor being allocated to a different region during evaluation, leading
to more memory fragmentation in our scratch buffer.
This recent commit guarantees uniform behavior of the allocator across
both the measurement and evaluation phases, eliminating discrepancies
between the two.
* metal: matrix-matrix multiplication kernel
This commit removes MPS and uses custom matrix-matrix multiplication
kernels for all quantization types. This commit also adds grouped-query
attention to support llama2 70B.
* metal: fix performance degradation from gqa
Integers are slow on the GPU, and 64-bit divides are extremely slow.
In the context of GQA, we introduce a 64-bit divide that cannot be
optimized out by the compiler, which results in a decrease of ~8% in
inference performance. This commit fixes that issue by calculating a
part of the offset with a 32-bit divide. Naturally, this limits the
size of a single matrix to ~4GB. However, this limitation should
suffice for the near future.
* metal: fix bugs for GQA and perplexity test.
I mixed up ne02 and nb02 in previous commit.
* server : implement json-schema-to-grammar.mjs by follow python impl
* server : add grammar support in chat.mjs
* server : implement grammer param in the UI
* server : generate .hpp
* server : remove trailing whitespaces
* server : generate .hpp
* server : fix sort of prop pairs
* server : optimize regex & iteration
* ggml-alloc: Don't try to re-use buffers of external tensors
They might be weights that came from another context, so we
have no control over them (and they might be re-used elsewhere
so writing to them would be a bad idea).
* ggml-alloc: >= when checking for out-of-bounds
Co-authored-by: slaren <slarengh@gmail.com>
---------
Co-authored-by: slaren <slarengh@gmail.com>
* add log_callback to llama_context_params for custom logging.
* Fix macro expansion on gcc
* Add struct llama_state for global variables and move log_callback there
* Turn log level into enum and some minor changes.
* Remove model_for_logging parameter (not needed anymore)
* Convert remaining fprintf(stderr, ...) calls to use new macros.
* Fix enum and initialize g_state
* Fix log calls after merge
* Fix missing static
* Add back all the new lines in the logging strings
* Add comment for llama_log_callback and replace remaining printf calls
---------
Co-authored-by: grahameth <->
Co-authored-by: Helmut <helmut.buhler@inf.h-brs.de>
* Update Vim plugin
* Remove getbufoneline usage, Add input bind example.
getbufoneline() appears to be a recently added function and has been
replaced with getbufline for compatibility.
An additional example that explains how to add a keybind that works in
insert mode was added.
