* Speedup tokenization
On current master it takes ~3.2 seconds to tokenize
Wikitext. With this change it becomes ~525 ms.
* Fixit: it was missing the piece after the last found occurence
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Make ggml-cuda.cu build with QK_K = 64
Using LLAMA_CUDA_FORCE_DMMV = ON and -nommq it runs and produces
a meaningful result.
* k_quants tuning for Falcon-7b
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* tests : write a Python tokenizer test (wip)
* llama : prefix input text for tokenization with whitespace
* llama : distinguish pieces from decoded text + fix detokenization
* common : add comments
* examples : no longer manually add leading space when tokenizing
* tests : use Python to generate tokenizer tests for C++
* tests : add option to tokenize text files
ggml-ci
* tests : add test-tokenizer-1.py
* llama.cpp : fix LF token
* hellaswag : move the concat space for clarity
* tests : add falcon tests (py + cpp, currently do not pass Unicode)
ggml-ci
* common : temporary separate llama_detokenize calls for SPM and BPE
---------
Co-authored-by: klosax <131523366+klosax@users.noreply.github.com>
The use of special characters within source files can break compiling on some computers with different region and language settings. Using Unicode escape sequences should allow for the code to be compiled on all setups without needing to change your computers settings or switch regions.
* llama.cpp : fix spm whitespace escaping + clean up
* main.cpp : spm - add whitespace in front of prompt
* test-tokenizer-0.cpp : spm - add whitespace in front of prompt
* Add llama_beam_search().
* Add '// Beam search' heading to llama.{h,cpp} after llama_grammar_accept_token().
* Add space around * pointers and & references.
* Add spaces around comparison and assignment operators.
* Prefer west const.
* Use llama_ prefix for structs in global namespace.
* Delete obsolete comment from an earlier revision.
* Change eos to eob in llama_beam and llama_beam_view structs.
* use hipblas based on cublas
* Update Makefile for the Cuda kernels
* Expand arch list and make it overrideable
* Fix multi GPU on multiple amd architectures with rocblas_initialize() (#5)
* add hipBLAS to README
* new build arg LLAMA_CUDA_MMQ_Y
* fix half2 decomposition
* Add intrinsics polyfills for AMD
* AMD assembly optimized __dp4a
* Allow overriding CC_TURING
* use "ROCm" instead of "CUDA"
* ignore all build dirs
* Add Dockerfiles
* fix llama-bench
* fix -nommq help for non CUDA/HIP
---------
Co-authored-by: YellowRoseCx <80486540+YellowRoseCx@users.noreply.github.com>
Co-authored-by: ardfork <134447697+ardfork@users.noreply.github.com>
Co-authored-by: funnbot <22226942+funnbot@users.noreply.github.com>
Co-authored-by: Engininja2 <139037756+Engininja2@users.noreply.github.com>
Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
Co-authored-by: jammm <2500920+jammm@users.noreply.github.com>
Co-authored-by: jdecourval <7315817+jdecourval@users.noreply.github.com>
* metal: better memory alloc w/ concurrency dispatch
The ggml-alloc should only free tensors at memory barriers.
* ggml-alloc: avoid return silently
In certain cases, the allocate_node() function may silently return
without performing any memory allocation.
* Improve UNK, BOS, EOS token handling when converting without metadata.
* Allow importing as a module.
* Remove some obsolete code and minor cleanups.
* Set default UNK token mapping from -1 to 0 in llama.cpp
* Try to handle overflow due to buggy Windows Python with a better error message
* Improve LLaMA-2 2-, 3- and 4-bit quantization
* Q3_K_S: use Q5_K for 1st 2 layers of attention.wv and feed_forward.w2
* Q4_K_S: use Q6_K for 1st 2 layers of attention.wv and feed_forward.w2
* Q2_K and Q3_K_M: use Q5_K instead of Q4_K for 1st 2 layers of
attention.wv and feed_forward.w2
This leads to a slight model sized increase as follows:
Q2_K : 2.684G vs 2.670G
Q3_K_S: 2.775G vs 2.745G
Q3_K_M: 3.071G vs 3.057G
Q4_K_S: 3.592G vs 3.563G
LLaMA-2 PPL for context 512 changes as follows:
Q2_K : 6.6691 vs 6.8201
Q3_K_S: 6.2129 vs 6.2584
Q3_K_M: 6.0387 vs 6.1371
Q4_K_S: 5.9138 vs 6.0041
There are improvements for LLaMA-1 as well, but they are
way smaller than the above.
* Minor 4-bit quantization improvement
For the same model size as previus commit, we get
PPL = 5.9069 vs 5.9138.
* Some more fine tuning
* Adding make_qkx2_quants
With it, we get PPL = 5.8828 for L2-7B Q4_K_S.
* Another minor improvement
* Q2_K improvement
Smaller model, lower perplexity.
7B: file size = 2.632G, PPL = 6.3772 vs original 2.670G PPL = 6.8201
12B: file size = 5.056G, PPL = 5.4577 vs original 5.130G PPL = 5.7178
It is mostly Q3_K except for tok_embeddings, attention.wq, attention.wk,
which are Q2_K
* Iterating
* Revert Q5_K back to make_qkx1_quants
* Better Q6_K
* make_qkx2_quants is better for Q5_K after all
* Fix after rebasing on master
* Fix for changed tensor names
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
use a different function for no_alloc to avoid breaking backwards compat, fixes lora
remove 512 n_batch limit
fixed 2048 batch size
cleanup
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* llama : add benchmark example
* add to examples CMakeLists.txt
* fix msvc build
* add missing include
* add Bessel's correction to stdev calculation
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* improve markdown formatting
* add missing include
* print warning is NDEBUG is not defined
* remove n_prompt and n_gen from the matrix, use each value separately instead
* better checks for non-optimized builds
* llama.cpp : fix MEM_REQ_SCRATCH0 reusing the value of n_ctx of the first call
* fix json formatting
* add sql output
* add basic cpu and gpu info (linx/cuda only)
* markdown: also show values that differ from the default
* markdown: add build id
* cleanup
* improve formatting
* formatting
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* 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.
* 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>
* added stream saving context data to file to avoid allocating unnecessary amounts of memory
* generalised copying state data to file or buffer
* added comments explaining how copy_state_data works
* fixed trailing whitespaces
* fixed save load state example
* updated save load state to use public function in llama.cpp
* - restored breakage of the llama_copy_state_data API
- moved new logic for copying llama state data to internal function
* fixed function declaration order
* restored save load state example
* fixed whitepace
* removed unused llama-util.h include
* Apply suggestions from code review
Co-authored-by: slaren <slarengh@gmail.com>
* Apply code review suggestions
Co-authored-by: slaren <slarengh@gmail.com>
---------
Co-authored-by: slaren <slarengh@gmail.com>
* ggml : add graph tensor allocator
* ggml : don't calculate data pointer of unallocated tensors when creating a view with an offset
* ggml : refactor ggml_view_Nd into ggml_view_tensor_offset
* ggml : graph allocation in contexts
* allocate work buffer as a ggml_object in ggml_graph_compute_with_ctx
* llama.cpp : allocate graph in the context
* add GGML_PAD
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
