* Use MTLDevice.newBufferWithBytesNoCopy to share buffers between CPU and GPU
* Page-align buffers used by Metal
* Remove trailing whitespace
* Only import unistd.h for Metal builds
* metal : remove unnecessary copies
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Starting to add k-quantization to ggml
I think it is better to have quantization separate from
ggml. For now just adding the k-quants there, but it would be
better to also factor out the existing ggml quantizations.
* Adding Q3_K and Q8_K (de)-quantization
* Q3_K now working on CUDA and AVX2/scalar
CUDA is not ideal - ~50% slower than Q4_0 for
single token prediction, about the same in batch
mode (perplexity). CPU single token is ~55 ms
(on Ryzen 7950X).
* Some improvement for Q3_K on CUDA
It is now ~22.5 ms/token on my GPU, so ~30% slower than Q4_0.
* Some more CUDA optimizations for Q3_K
Single token is now 20.5 ms/token (~20% slower than Q4_0).
Perplexity is on par with Q4_0.
* Adding Q4_K - scalar, AVX2, CUDA
Performance is the same or perhaps very slightly better than Q4_0 on the CPU.
On the GPU, single token prediction is ~10% better than Q4_0,
batch mode (perplexity is about the same).
* Adding Q6_K - scalar, AVX2, CUDA
Performance is ~40% lower compared to Q4_K on the CPU.
This is to be expected, considering that we are memory bound
on the CPU and the 6-bit model is ~44% larger than the 4-bit.
On the GPU, single token prediction is ~6% lower than Q4_0,
batch mode (perplexity) is even closer (but still slower).
* Adding Q5_K - scalar, AVX2, CUDA
Performance is ~20% lower compared to Q4_K on the CPU.
This is to be expected, considering that we are memory bound
on the CPU and the 5-bit model is ~22% larger than the 4-bit.
On the GPU, single token prediction is about the same as Q4_0
for both, single token and batch prediction.
* Per convention, all QX_K quantizations use Q5_K for output.weight
* Adding quantization mixes
* Quantization mixes: didn't quite get what I wanted in the last commit
* Q4_K dot product for ARM_NEON
* Q6_K dot product for ARM_NEON
* Q5_K dot product for ARM_NEON
* Adding Q3_K dot for ARM_NEON
It is 22% slower than Q4_K, despite the smaller model size.
On x86_64, where we are memory bound, the Q3_K model is
quite a bit faster than Q4_K.
* A very slightly faster ARM_NEON Q3_K dot
* Adding Q2_K - just CUDA for now
Token prediction is pretty good - about 15.5 ms on a RTX 4080.
Perplexity is about the same as Q4_K.
* Adding scalar and AVX2 Q2_K dot
* Adding ARM_NEON Q2_K dot
About the same performance as Q4_K.
* A slightly faster ARM_NEON Q2_K dot
Single token prediction is now ~36 ms on M2 Max.
The code is much simpler too.
* Fixed bug in Q2_K CUDA dot product kernel
Stranegly enough, for the few prompts I tried with the 7B model
the responses looked perfectly reasonable. Only realized something
is not quite right when I tried the larger models and started getting
nonse back.
In any case, Q2_K single token evaluation time on an RTX 4080 in a Ryzen7950X
box iusing CUDA and model fully loaded on the GPU are
~15.5 ms for 7B, ~25.4 ms for 13B, and ~55.8 ms for 30B.
The max number of layers that fit in VRAM for The 65B is 32.
With that, we get ~330 ms per token, which is not that much faster
than just running on the CPU (~470 ms per token).
* Don't print zeros/NaNs when no count histogram has been collected
* A 10% faster CUDA vector dot kernel for Q3_K
Q3_K is now running at ~18.5 ms / token on CUDA,
so the gap to Q4_0 is only 10%.
It seems memory acccess pattern is more important for
performance than the amount of computation the kernel
does.
* A slightly daster Q4_K AVX2 dot product
For perplexity, where we are less memory bound, time per
pass drops by ~5%. Barely measurable difference for single
token prediction.
* A slightly faster ARM_NEON A4_K dot product
* Minor
* Fix quantization error test
We cannot possibly be expecting rmse < 0.002 for 2- and 3-bit
quantization variants.
* Fix docker build
I have been sloppy with vector reinterpret casts on ARM_NEON.
It seems clang is very forgiving in that regard.
* Added forgotten ggml.o dependence on k_quants.h to the Makefile
* Had unintentionally committed the Makefile with -Ofast enabled
* ggml : rename k_quants -> ggml-quants-k, use lowercase in code
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* mtl : export the LLaMA computation graph
* ci : disable temporary
* mtl : adapt the MNIST example as starter
* mtl : no need for mtl-export tool, add cli arg for main instead
* mtl : export just a small part of the graph for now to make it easier
* mtl : move MSL code into separate file for easy editing
* mtl : initial get_rows_q4_0 kernel
* mtl : confirmed get_rows_q4_0 is working correctly
* mtl : add rms_norm kernel + confirm working
* mtl : add mul kernel + confirm working
* mtl : initial mul_mat Q4 kernel (wrong results)
* mtl : mul_mat fixes (still wrong)
* mtl : another mul_mat Q4 (still does not work)
* mtl : working mul_mat q4
* ggml : fix handling of "view" ops in ggml_graph_import()
* mtl : add rope kernel
* mtl : add reshape and transpose handling
* ggml : store offset as opt arg for ggml_view_xd() operators
* mtl : add cpy kernel + handle view ops
* mtl : confirm f16 x f32 attention mul mat
* mtl : add scale kernel
* mtl : add diag_mask_inf kernel
* mtl : fix soft_max kernel
* ggml : update ggml_nbytes() to handle non-contiguous tensors
* mtl : verify V tensor contents
* mtl : add f32 -> f32 cpy kernel
* mtl : add silu kernel
* mtl : add non-broadcast mul kernel
* mtl : full GPU inference of the computation graph
* mtl : optimize rms_norm and soft_max kernels
* mtl : add f16 mat x f32 vec multiplication kernel
* mtl : fix bug in f16 x f32 mul mat + speed-up computation
* mtl : faster mul_mat_q4_0_f32 kernel
* mtl : fix kernel signature + roll inner loop
* mtl : more threads for rms_norm + better timing
* mtl : remove printfs from inner loop
* mtl : simplify implementation
* mtl : add save/load vocab to ggml file
* mtl : plug Metal inference into llama.cpp (very quick-n-dirty)
* mtl : make it work with main example
Lots of hacks but at least now it generates text
* mtl : preparing for merge
* mtl : clean-up ggml mtl interface + suport scratch / inplace
* mtl : remove temp / debug code
* metal : final refactoring and simplification
* Revert "ci : disable temporary"
This reverts commit 98c267fc77.
* metal : add comments
* metal : clean-up stuff, fix typos
* readme : add Metal instructions
* readme : add example for main
* Use events instead of clFinish, where possible
* OpenCL: Don't load gpu layers into RAM, add mul_f32 kernel
* Reduce queueing overhead for contiguous tensors by using single mul kernel call
* Adapt to #1612 cl_mem malloc changes
* Reduce code duplication between cuda and opencl branches
* Improve implementation
* Move back to C++ for OpenCL
* Refactor OpenCL code to work more like the CUDA code, add missing functions
* Deduplicate dequant kernels
* Add OpenCL compile options
* Use compile args for preprocessing constants
* Restore default platform + device selection by id behavior
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Henri Vasserman <henv@hot.ee>
* Broadcasting for ggml_mul
* CUDA kernel for ggml_mul, norms in VRAM
* GPU weights not in RAM, direct loading with cuFile
* fixup! GPU weights not in RAM, direct loading with cuFile
* fixup! GPU weights not in RAM, direct loading with cuFile
* define default model path once, sync path with readme (#1366)
* ~7% faster Q5_1 AVX2 code (#1477)
* convert.py: Support models which are stored in a single pytorch_model.bin (#1469)
* Support models in a single pytorch_model.bin
* Remove spurious line with typo
* benchmark-matmul: Print the average of the test results (#1490)
* Remove unused n_parts parameter (#1509)
* Fixes#1511 lambda issue for w64devkit (mingw) (#1513)
* Fix for w64devkit and mingw
* make kv_f16 the default for api users (#1517)
* minor : fix compile warnings
* readme : adds WizardLM to the list of supported models (#1485)
* main : make reverse prompt option act as a stop token in non-interactive mode (#1032)
* Make reverse prompt option act as a stop token in non-interactive scenarios
* Making requested review changes
* Update gpt_params_parse and fix a merge error
* Revert "Update gpt_params_parse and fix a merge error"
This reverts commit 2bb2ff1748.
* Update gpt_params_parse and fix a merge error take 2
* examples : add persistent chat (#1495)
* examples : add persistent chat
* examples : fix whitespace
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* tests : add missing header
* ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508)
* ggml : use F16 instead of F32 in Q4_0, Q4_1 and Q8_0
* llama : bump LLAMA_FILE_VERSION to 3
* cuda : update Q4 and Q8 dequantize kernels
* ggml : fix AVX dot products
* readme : update performance table + hot topics
* ggml : fix scalar implementation of Q4_1 dot
* llama : fix compile warnings in llama_set_state_data()
* llama : fix name shadowing and C4146 (#1526)
* Fix name shadowing and C4146
* Fix if macros not using defined when required
* Update llama-util.h
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Update llama-util.h
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Code style
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Fix for mingw (#1462)
* llama : add llama_init_backend() API (close#1527)
* feature : add blis and other BLAS implementation support (#1502)
* feature: add blis support
* feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927
* fix: version detection for BLA_SIZEOF_INTEGER, recover min version of cmake
* Fix typo in INTEGER
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Revert "feature : add blis and other BLAS implementation support (#1502)"
This reverts commit 07e9ace0f9.
* GPU weights not in RAM, direct loading with cuFile
* llama : code style fixes + progress print fix
* ggml : ggml_mul better broadcast support
* cmake : workarounds for cufile when CMake version < 3.25
* gg rebase fixup
* Loop in llama.cpp, fixed progress callback
* Attempt clang-tidy fix
* llama : fix vram size computation
* Add forgotten fclose()
---------
Co-authored-by: András Salamon <ott2@users.noreply.github.com>
Co-authored-by: Ilya Kurdyukov <59548320+ilyakurdyukov@users.noreply.github.com>
Co-authored-by: Tom Jobbins <784313+TheBloke@users.noreply.github.com>
Co-authored-by: rankaiyx <rankaiyx@rankaiyx.com>
Co-authored-by: Stephan Walter <stephan@walter.name>
Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com>
Co-authored-by: Erik Scholz <Green-Sky@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: David Kennedy <dakennedyd@gmail.com>
Co-authored-by: Jason McCartney <jmac@theroot.org>
Co-authored-by: Evan Jones <evan.q.jones@gmail.com>
Co-authored-by: Maxime <672982+maximegmd@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Zenix <zenixls2@gmail.com>
* Fix name shadowing and C4146
* Fix if macros not using defined when required
* Update llama-util.h
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Update llama-util.h
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Code style
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* fix race condition bug in non-inplace ggml_compute_forward_diag_mask_f32
memcpy needs to be synchronized across threads to avoid race conditions.
=> do it in INIT phase
* remove trailing whitespace
* Update ggml.c
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* implement 8 of 14 missing backward pass operations used by llama
- GGML_OP_ADD_AT
- GGML_OP_CPY
- GGML_OP_MUL_MAT (src0.grad)
- GGML_OP_PERMUTE
- GGML_OP_RESHAPE
- GGML_OP_SCALE
- GGML_OP_TRANSPOSE
- GGML_OP_VIEW
implement additional ggml operation GGML_OP_ADD_AT, which is necessary for backward pass of GGML_OP_VIEW.
this operation adds src1 to src0 with data offset, i.e. to view(src0, ..., offset).
the values are return in a tensor size of src0. values outside of [data+offset:data+offset+nbytes(src1)] are just the original values from src0.
still missing backward passes for llama:
- GGML_OP_DIAG_MASK_INF
- GGML_OP_GET_ROWS
- GGML_OP_RMS_NORM
- GGML_OP_ROPE
- GGML_OP_SILU
- GGML_OP_SOFT_MAX
* implement 5 of 6 missing backward pass operations used by llama
- GGML_OP_DIAG_MASK_INF
- GGML_OP_GET_ROWS
- GGML_OP_RMS_NORM
- GGML_OP_SILU
- GGML_OP_SOFT_MAX
add necessary ggml operations GGML_OP_ADD1, GGML_OP_SILU_BACK, GGML_OP_RMS_NORM_BACK, GGML_OP_DIAG_MASK_ZERO, and GGML_OP_ROPE_BACK
GGML_OP_ADD1 is necessary to add a scalar value in the backward pass of GGML_OP_SOFT_MAX
GGML_OP_ADD1 could also be replaced by using GGML_OP_ADD and GGML_OP_REPEAT, but the performance would be worse. additionally GGML_OP_REPEAT will return unexpected value when the the input to GGML_OP_SOFT_MAX contains only a single scalar. in this case GGML_OP_REPEAT will not return the value that should be repeated (src1) but the value which shape the result should take (src0). So in this case it can not replace GGML_OP_ADD1.
GGML_OP_SILU_BACK, GGML_OP_RMS_NORM_BACK and GGML_OP_ROPE_BACK are necessary for backward pass of GGML_OP_SILU, GGML_OP_RMS_NORM and GGML_OP_ROPE. The backward pass for these functions cannot be easily composed of existing operations. Since the backward pass builds a computation graph we need operations forward pass implementations of the the required backward passes. Sounds a bit confusing at first, I know...
GGML_OP_DIAG_MASK_ZERO is necessary for backward pass of GGML_OP_DIAG_MASK_INF.
Some operations where previously inplace-only. for backward pass there needs to be non-inplace variants.
staying consistent with other operations that have non-inplace and inplace variants, the operations are changed to non-inplace and
functions with "_inplace" are added which are inplace.
in llama we need to call the inplace variants so that it is implemented as before.
for llama backward pass we need to use the non-inplace variants.
still not completely implemented backward passes for llama:
- GGML_OP_ROPE: needs forward pass for GGML_OP_ROPE_BACK
- GGML_OP_GET_ROWS: only necessary for tokenizer
* norm & rms_norm can not be threaded:
after investigation rms norm for quite some time I come to the conclusion that neither norm, nor rms_norm can be threaded, because we need mean over all items, not just of the slices each thread sees.
* remove already resolved TODO
* implement backward pass of ggml_rope and ggml_rope_back
* implement backward pass for ggml_get_rows and for new operation ggml_get_rows_back
* add test-grad0.c
* use GGML_PRINT_DEBUG for debug messages which will otherwise flood the console
* test both gradients of mul_mat
* disable graph dot export as it floods console
* bug fixes for silu_back
* successfully test silu backward
* bug fix for scale backward pass
use sum instead of mean for gradient of scalar scale parameter
* successfully test scale backward
* improve performance of sum backward pass
use add1(x,y) instead of add(x,repeat(y,x))
* improve performance of sqr backward pass
use scale(x,y) instead of mul(x,repeat(y,x))
* successfully test rope backward
* bug fix for cpy backward pass
* successfully test cpy backward
* bug fix for reshape backward pass
* successfully test reshape backward
* add test-opt.c
this uses ggml_opt to train a,b for minimal e=sum(sqr(c - a*b)) for random initial a,b,c
* correctly implement softmax backward pass using new operation ggml_diag
ggml_diag constructs diagonal matrices with entries.
ggml_diag(shape[a,1,c,d]) -> shape[a,a,c,d]
* successfully test soft_max backward
* align shape annotations
* add shape annotations for llama
* de-duplicate ggml_forward_dup code taking care of contiguous tensors of same type.
with this we can duplicate tensor of any typ as long as they are contiguous.
* fix ggml_compute_forward_dup_same_cont for when nelements < nthreads
when more threads are used than elements exist ie1 was less than ie0, resulting in invalid negative byte count argument in memcpy
* bug fix for add_at forward
required for view backward pass
src0 values must be copied to dst, because during addition we don't touch all dst elements in contrast to the normal add function.
* successfully test view backward
* minor code format improvement
* fix ggml_forward_add functions to work correctly with transposed tensors
uses the same logic as in ggml_compute_forward_add_q_f32, but make it consistent across all ggml_compute_forward_add_... functions.
this also slightly changes the mem access pattern of the different threads to works as in ggml_compute_forward_add_q_f32.
* fix ggml_forward_add1 functions to work correctly with transposed tensors
uses the same logic as in ggml_compute_forward_add1_q_f32, but make it consistent across all ggml_compute_forward_add1_... functions.
this also slightly changes the mem access pattern of the different threads to works as in ggml_compute_forward_add1_q_f32.
* test-grad0.c : add print_elements to help with debugging
* successfully test permute backward
* some minor test-grad0 fixes
* fix sub, mul and div functions to work correctly with transposed tensors
uses the same logic as in add
* implement ggml_cont backward pass
* successfully test transpose backward and permute for all permutations
also test sub, mul and div up to max n_dims
* test-grad0.c add TODO for view_2d and view_3d
add_at (required for view backward pass) is a bit tricky for n_dims > 1.
* fix comments
* successfully test diag_mask_inf and diag_mask_zero backward
* test-grad0 : fix test for div
nargs and ndims was swapped, corrupting the stack
* fix diag_mask to work with non-inplace input
* move dup call into the actual add_at functions
* fix get rows backward pass
* successfully test get_rows backward
* fix view backward pass
add nb parameters to add_at like in view.
together with offset they define how to view dst and src0 during the add_at operation.
* successfully test backward pass of view_1d, view_2d and view_3d
* fix backward pass for rms_norm
I would have used formulas from other frameworks, but they differed so I could not decide which is correct.
Instead it was derived here in comment using manual forward-backward automatic differention of rms_norm and simplification.
* successfully test backward pass of rms_norm
some tests may fail when gradients are large.
could not find a satisfying configuration to check for abs error and relative error that passes all tests while still actually testing the results with tight enough error bounds.
when looking at the values the "failed" tests look actually ok. for example:
rms_norm: ndims=2, i=0, k=2, x0=0.000153, xm=0.000053, xp=0.000253, f0=0.278594, f1=0.086213, g0=961.905457, g1=966.064941, eps=0.000100, error_abs=4.159485, error_rel=0.004324
it is due to the test logic in check_gradients that they fail.
* add todos for llama backward pass
- implementation for ADD1 backward pass should probably use sum instead of mean (but this backward pass is not required)
- repeat is not yet tested and looks like it only works for single element src0 inputs.
* add operation ggml_sum_rows
ggml_sum_rows(shape[a,b,c,d]) -> shape[1,b,c,d]
* add missing GGML_OP_SUM_ROWS
* fix backward pass for repeat
requires ggml_sum_rows
* successfully test backward pass of repeat
* update quantization types in switch-case of add_at and add1
* add baby-llama example training a very small llama model from scratch to output a sinusoidal wave.
had to increase maximum number of optimization parameters to train from scratch.
* fix softmax in baby-llama example
* switching from training with adam to lbfgs produces much better results in the baby-llama example
* train with two examples, creating new tensors each time..
* fix bug when using ggml_opt to optimize params in one context and use a renewable context for eval and opt
when not keeping gradients of model parameters they are overwritten by tensors created by opt, which may be invalid after opt context is renewed.
so we need to keep the original gradients and make dups for opt
* train on multiple examples, generate & print tokens with trained model afterwards
ctx0 for evaluation and optimization is renewed for each sample
* add ggml_reshape_1d, ggml_reshape_4d and ggml_view_4d
* fix soft_max backward pass for input->ne[1] != 1
* add ggml_log operation necessary for cross entropy loss
* add test for ggml_log gradients
* implement backward pass for ggml_sum_rows, necessary for cross entropy loss
* implement ggml_repeat support for rank > 2 tensors
* add test for ggml_sum_rows gradients
* fix training get_example_targets
predict the next token, not the current token!
* add square_error_loss and cross_entropy_loss functions
* optimize loss over multiple samples
this increases computation graph, need parallel batched forward for more efficiency.
* fix backward pass for add_at and change arguments to have same order as in view
* add ggml_set(ctx, a, b) to set b in view of a and return modified a
necessary to set values into kv_self cache and properly propagate the gradients
* fix kv_self gradients for training
use ggml_set instead of ggml_cpy to set kv_self cache with properly propagating gradients
* replace inplace operations for training with copying operations to allow gradient propagation
* add GGML_ASSERT to catch ggml_rope and back value errors
* add trainable lora-only model with all big matrices C split into A,B with A*B=C
this is not a lora-finetune, but the whole model changed to have only low-rank "lora" matrices.
training this instead of the normal model resulted in much worse results though...
* vastly improve training results
instead of logit targets 0 and 1 use -1 and +1.
* shorten code using a variable
* change name of GGML_OP_ADD_AT to GGML_OP_ACC
* smaller default values for baby llama model parameters
* update static assert of GGML_OP_COUNT
* remove shape annotations in llama_eval_internal
* revert disabling of threading for rms_norm and norm
* rename print functions in baby-llama example
* fix call to ggml_set_name
* add missing include for strcmp, etc
* remove trailing whitespace
* reduce number of test-grad0 iterations
avoid exceeding timeout of automated tests
* remove busy loop that was used as sleep for slower sinus wave generation
* disable slow tests grad0 and opt to avoid exceeding timeouts
* c++ in baby-llama example
use c++ includes instead of c includes
use std::min, std::max instead of MIN, MAX macros
* c++ in baby-llama example
use c++ includes instead of c includes
use std::min, std::max instead of MIN, MAX macros
* ggml : fix compiler warnings + cosmetic changes
* ggml : fix nullptr derefs in GGML_OP_CONT and GGML_OP_RESHAPE back
* swap arguments to vDSP_vdiv call
documentation for vDSP_vdiv states: "Note that B comes before A!"
* swap arguments to vDSP_vdiv call
documentation for vDSP_vdiv states: "Note that B comes before A!"
* ggml : swap vDSP_vsub args as per documentation
* add parallel batched forward function for baby-llama training
* cleanup code for batched training
* remove trailing whitespace
* minor : fix compiler warnings + indentation style
* ggml : fix null ptr deref in backward pass
* ggml : remove Q4_2 remnants
* ggml : fix clang-tidy warnings
* baby-llama : couple of clang-tidy warnings
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler
Tested with a 13B model.
* use _mm_pause() in busyloop
* use _mm_pause() in busyloop on x86_64 to reduce power consumption
Minor edit in ggml.c which originally would prevent OpenCL from loading completely if GGML_USE_ACCELERATE was defined.
Minor speedup in prompt eval time.
* change immintrin.h to intrin.h for compatibility
Building on windows11 arm throws an error on this line. Seems like using intrin.h covers x86 and and arm
* conditional def of intrin.h
* fix typo in ggml.c
* llama : minor - remove explicity int64_t cast
* ggml : reduce memory buffer for F16 mul_mat when not using cuBLAS
* ggml : add asserts to guard for incorrect wsize
* Allow use of OpenCL GPU-based BLAS using ClBlast instead of OpenBLAS for context processing
* Improve ClBlast implementation, avoid recreating buffers, remove redundant transfers
* Finish merge of ClBlast support
* Move CLBlast implementation to separate file
Add buffer reuse code (adapted from slaren's cuda implementation)
* Add q4_2 and q4_3 CLBlast support, improve code
* Double CLBlast speed by disabling OpenBLAS thread workaround
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
Co-authored-by: slaren <2141330+slaren@users.noreply.github.com>
* Fix device selection env variable names
* Fix cast in opencl kernels
* Add CLBlast to CMakeLists.txt
* Replace buffer pool with static buffers a, b, qb, c
Fix compile warnings
* Fix typos, use GGML_TYPE defines, improve code
* Improve btype dequant kernel selection code, add error if type is unsupported
* Improve code quality
* Move internal stuff out of header
* Use internal enums instead of CLBlast enums
* Remove leftover C++ includes and defines
* Make event use easier to read
Co-authored-by: Henri Vasserman <henv@hot.ee>
* Use c compiler for opencl files
* Simplify code, fix include
* First check error, then release event
* Make globals static, fix indentation
* Rename dequant kernels file to conform with other file names
* Fix import cl file name
---------
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
Co-authored-by: slaren <2141330+slaren@users.noreply.github.com>
Co-authored-by: Henri Vasserman <henv@hot.ee>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Use full range for q4_0 quantization
By keeping the sign of the highest magnitude, we can make sure the
highest value maps to -8, which is currently unused.
This is a bit of a freebie since it is fully backwards compatible with
the current format.
* Update quantize_row_q4_0 for AVX/AVX2
* Update quantize_row_q4_0 for WASM
Untested
* Update quantize_row_q4_0 for Arm NEON
* Update quantize_row_q4_0 for PowerPC
Untested
* Use full range for q4_2 quantization
* ggml : prefer vzip to vuzp
This way we always use the same type of instruction across all quantizations
* ggml : alternative Q4_3 implementation using modified Q8_0
* ggml : fix Q4_3 scalar imlpementation
* ggml : slight improvement of Q4_3 - no need for loop unrolling
* ggml : fix AVX paths for Q8_0 quantization
* Improve cuBLAS performance by using a memory pool
* Move cuda specific definitions to ggml-cuda.h/cu
* Add CXX flags to nvcc
* Change memory pool synchronization mechanism to a spin lock
General code cleanup
* A faster version for Q4_1 x Q8_0 dot products
The idea nehind being that Q8_0 quantized
values get used many times in the matrix multiplications
where they are involved. In the current implementations,
when we are evaluating the dot products, we need to compute
the sum of the quants in the Q8_0 vector, so the same
operation is repeated many times. Here we pre-compute
the sum during Q8_0 quantization, store it in the
now modified block_q8_0 struct, and then reuse this
result in the subsequent dot products.
In a synthetic benchmark (just compute a bunch of dot
products), this change speeds up the Q4_1 * Q8_0 dot
product by 80%, making the performance identical to
Q4_0 * Q8_0.
In practical application, I see a ~15% gain in speed for
token prediction on M2, and ~5% gain on Ryzen 7950X.
The speed gain in the prompt evaluation is much bigger
(around 50%).
I have only done the change for the scalar version,
ARM_NEON, and AVX2, so we still need an AVX implementation.
* Cleaning up
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Multi-threading quantization.
Not much gain for simple quantizations, bit it will be important
for quantizations that require more CPU cycles.
* Multi-threading for quantize-stats
It now does the job in ~14 seconds on my Mac for
Q4_0, Q4_1 and Q4_2. Single-threaded it was taking
more than 2 minutes after adding the more elaborate
version of Q4_2.
* Reviewer comments
* Avoiding compiler confusion
After changing chunk_size to const int as suggested by
@ggerganov, clang and GCC starting to warn me that I don't
need to capture it in the lambda. So, I removed it from the
capture list. But that makes the MSVC build fail. So,
making it a constexpr to make every compiler happy.
* Still fighting with lambda captures in MSVC
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Q4_2 quantization with rmse-optimized scale and quants
For quantize-stats we get
q4_2: rmse 0.00159301, maxerr 0.17480469, 95pct<0.0030, median<0.0012
For 7B perplexity with BLAS enabled we get 6.2038 after 655 chunks.
Quantization is slow (~90 seconds on my Mac for 7B) as not
multi-threaded as in PR #896.
* ggml : satisfy the sanitizer builds
Not sure why this makes them fail
* Better follow ggml conventions for function names
* Fixed type as per reviewer comment
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* GGML map ops proof of concept.
* Various cleanups.
Add handling for task setting.
Add handling for ggml_compute_backward.
Rename functions to ggml_map_unary_f32 and ggml_map_binary_f32
Fix compiler warnings related to casting function pointers and `void *`
Reorder functions and definitions based on the GGML op number.
Use typedefs for map op function pointer types.
* Fix position of map ops cases in ggml_compute_forward
Mostly for msys2 and mingw64 builds, which are different from each other
and different from standard Visual Studio builds. Isn't Windows fun?
- Define _GNU_SOURCE in more files (it's already used in ggml.c for
Linux's sake).
- Don't use PrefetchVirtualMemory if not building for Windows 8 or later
(mingw64 doesn't by default). But warn the user about this situation
since it's probably not intended.
- Check for NOMINMAX already being defined, which it is on mingw64.
- Actually use the `increment` variable (bug in my `pizza` PR).
- Suppress unused variable warnings in the fake pthread_create and
pthread_join implementations for Windows.
- (not Windows-related) Remove mention of `asprintf` from comment;
`asprintf` is no longer used.
Fixes#871.
- Support all three formats (ggml, ggmf, ggjt). (However, I didn't
include the hack needed to support GPT4All files without conversion.
Those can still be used after converting them with convert.py from my
other PR.)
- Support both mmap and read (mmap is used by default, but can be
disabled with `--no-mmap`, and is automatically disabled for pre-ggjt
files or on platforms where mmap is not supported).
- Support multi-file models like before, but automatically determine the
number of parts rather than requiring `--n_parts`.
- Improve validation and error checking.
- Stop using the per-file type field (f16) entirely in favor of just
relying on the per-tensor type/size fields. This has no immediate
benefit, but makes it easier to experiment with different formats, and
should make it easier to support the new GPTQ-for-LLaMa models in the
future (I have some work in progress on that front).
- Support VirtualLock on Windows (using the same `--mlock` option as on
Unix).
- Indicate loading progress when using mmap + mlock. (Which led me
to the interesting observation that on my Linux machine, with a
warm file cache, mlock actually takes some time, whereas mmap
without mlock starts almost instantly...)
- To help implement this, move mlock support from ggml to the
loading code.
- madvise/PrefetchVirtualMemory support (based on #740)
- Switch from ifstream to the `fopen` family of functions to avoid
unnecessary copying and, when mmap is enabled, allow reusing the same
file descriptor for both metadata reads and mmap (whereas the existing
implementation opens the file a second time to mmap).
- Quantization now produces a single-file output even with multi-file
inputs (not really a feature as much as 'it was easier this way').
Implementation notes:
I tried to factor the code into more discrete pieces than before.
Regarding code style: I tried to follow the code style, but I'm naughty
and used a few advanced C++ features repeatedly:
- Destructors to make it easier to ensure everything gets cleaned up.
- Exceptions. I don't even usually use exceptions when writing C++, and
I can remove them if desired... but here they make the loading code
much more succinct while still properly handling a variety of errors,
ranging from API calls failing to integer overflow and allocation
failure. The exceptions are converted to error codes at the
API boundary.)
Co-authored-by: Pavol Rusnak <pavol@rusnak.io> (for the bit I copied from #740)
Command that calculates some statistics over the errors introduced by
quantization, like mean square error, max error and some percentile errors for layer
weights. Should be useful for testing quantization improvements.
Exposes some internal state from ggml and llama for testing
ggml :
- added ggml_view_3d()
- ggml_view_tensor() now inherits the stride too
- reimplement ggml_cpy() to account for dst stride
- no longer require tensor->data to be memory aligned
llama :
- compute RoPE on 32-bit tensors (should be more accurate)
- store RoPE-ed K in the KV cache
- store transposed V in the KV cache (significant speed-up)
- avoid unnecessary Q copy
* It seems some new warning were added recently that exposed this. I wrote the code that included this unused variable originally and it is indeed not needed.
* Enable Fused-Multiply-Add (FMA) instructions on MSVC
__FMA__ macro does not exist in MSVC
* Enable F16C/CVT16 vector extensions on MSVC
__F16C__ macro does not exist in MSVC, but is implied with AVX2/AVX512
* MSVC cvt intrinsics
* Add __SSE3__ macro for MSVC too because why not
even though it's not currently used for anything when AVX is defined
* Add AVX2 implementation of quantize_row_q4_1
* Actually use AVX2
* Make quantize_row_q4_1 static
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Be more strict about converting float to double
* Test equivalence of round, SILU implementations
Test module is commented out in CMakeLists.txt because the tests may
take a long time, depending on how much the compiler optimizes.
* Fix softmax in perplexity.cpp
* all : prefer float over double where appropriate
* perplexity : add <cmath>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
- main -> examples
- utils -> examples (renamed to "common")
- quantize -> examples
- separate tools for "perplexity" and "embedding"
Hope I didn't break something !
* Retire the ggml_mul_mat() for transposed src0
- It can always be made contiguous with ggml_cpy()
- The code is now simplified
- The results are deterministic in respect to num threads
* SIMD-ify dequantize_row_q4_0() for ARM_NEON (#502)
* Attempt to SIMD-ify dequantize_row_q4_0() for ARM_NEON
* Fix dequantization - forgot to interleave the quants
* Reduce memory usage and allocate enough memory for large contexts
* Simpler scratch buffer usage
* Reenable BLAS for quantized mul_mat
* Fix number of layers in 30B and 65B
* Fix KV cache size for F32
* Support calling mlock() on loaded model data on Linux and macOS
This is enabled by a new --mlock command line option.
Using mlock() disables swapping and memory compression for the model
data. Doing so can be useful on systems where the model takes up a
large fraction of system RAM. In my experience, macOS is quite eager to
start compressing llama.cpp's memory, which then makes it halt for a few
seconds while it decompresses, even with a model that uses "only" 25GB
out of 32GB.
Of course, this comes at the cost of forcing the system to swap or
compress other processes' memory instead, so it needs to be used with
care and shouldn't be enabled by default.
In theory it should be possible to support this on Windows as well using
VirtualLock(), but I'm not much of a Windows user.
* Update llama.cpp
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Deduplicate q4 quantization functions
* Use const; add basic test
* Re-enable quantization test
* Disable AVX2 flags in CI
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Major refactoring - introduce C-style API
* Clean up
* Add <cassert>
* Add <iterator>
* Add <algorithm> ....
* Fix timing reporting and accumulation
* Measure eval time only for single-token calls
* Change llama_tokenize return meaning
* Update Makefile to detect AVX512 support and add compiler flags if it's available
* Based on existing AVX2 implementation, dot product on one 32-value block of 4-bit quantized ints at a time
* Perform 8 bit -> 16 bit sign extension and multiply+add on 32 values at time instead of 16
* Use built-in AVX512 horizontal reduce add to get sum at the end
* Manual unrolling on inner dot product loop to reduce loop counter overhead
The readme tells people to use the command line option "-t 8", causing 8
threads to be started. On systems with fewer than 8 cores, this causes a
significant slowdown. Remove the option from the example command lines
and use /proc/cpuinfo on Linux to determine a sensible default.
* Add AVX2 version of ggml_vec_dot_q4_1
* Small optimisations to q4_1 dot product (@Const-me)
* Rearrange Q4_1 quantization to work for multipart models. (Fix#152)
* Fix ggml_vec_mad_q4_1 too
* Fix non-vectorised q4_1 vec mul
* Don't use vdotq_s32 if it's not available
`dotprod` extensions aren't available on some ARM CPUs (e.g. Raspberry Pi 4), so check for them and only use them if they're available.
Reintroduces the code removed in 84d9015 if `__ARM_FEATURE_DOTPROD` isn't defined.
* Update ggml.c
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Apply fixes suggested to build on windows
Issue: https://github.com/ggerganov/llama.cpp/issues/22
* Remove unsupported VLAs
* MSVC: Remove features that are only available on MSVC C++20.
* Fix zero initialization of the other fields.
* Change the use of vector for stack allocations.
