Commit graph

200 commits

Author SHA1 Message Date
clyang
3bbc1a11f0
ggml : fix buidling with Intel MKL but ask for "cblas.h" issue (#2104) (#2115)
* Fix buidling with Intel MKL but ask for "cblas.h" issue

* Use angle brackets to indicate the system library
2023-07-09 11:12:20 +03:00
Qingyou Meng
1d656d6360
ggml : change ggml_graph_compute() API to not require context (#1999)
* ggml_graph_compute: deprecate using ggml_context, try resolve issue #287

* rewrite: no longer consider backward compitability; plan and make_plan

* minor: rename ctx as plan; const

* remove ggml_graph_compute from tests/test-grad0.c, but current change breaks backward

* add static ggml_graph_compute_sugar()

* minor: update comments

* reusable buffers

* ggml : more consistent naming + metal fixes

* ggml : fix docs

* tests : disable grad / opt + minor naming changes

* ggml : add ggml_graph_compute_with_ctx()

- backwards compatible API
- deduplicates a lot of copy-paste

* ci : enable test-grad0

* examples : factor out plan allocation into a helper function

* llama : factor out plan stuff into a helper function

* ci : fix env

* llama : fix duplicate symbols + refactor example benchmark

* ggml : remove obsolete assert + refactor n_tasks section

* ggml : fix indentation in switch

* llama : avoid unnecessary bool

* ggml : remove comments from source file and match order in header

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-07 19:24:01 +03:00
Georgi Gerganov
7242140283 ggml : remove sched_yield() call in ggml_graph_compute_thread() (#2134) 2023-07-07 18:37:10 +03:00
Georgi Gerganov
ec326d350c
ggml : fix bug introduced in #1237 2023-07-05 20:44:11 +03:00
Stephan Walter
1b107b8550
ggml : generalize quantize_fns for simpler FP16 handling (#1237)
* Generalize quantize_fns for simpler FP16 handling

* Remove call to ggml_cuda_mul_mat_get_wsize

* ci : disable FMA for mac os actions

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-07-05 19:13:06 +03:00
Georgi Gerganov
ed9a54e512
ggml : sync latest (new ops, macros, refactoring) (#2106)
- add ggml_argmax()
- add ggml_tanh()
- add ggml_elu()
- refactor ggml_conv_1d() and variants
- refactor ggml_conv_2d() and variants
- add helper macros to reduce code duplication in ggml.c
2023-07-04 21:54:11 +03:00
Georgi Gerganov
46088f7231 ggml : fix build with OpenBLAS (close #2066) 2023-07-02 09:46:46 +03:00
Qingyou Meng
b1ca8f36a9
ggml : disable GGML_TASK_INIT and GGML_TASK_FINALIZE by default (#1995)
Will not be scheduled unless explicitly enabled.
2023-07-01 18:42:43 +03:00
Erik Scholz
9d23589d63
fix pthreads setaffinity usage on android (#2020) 2023-06-27 19:06:33 +02:00
Georgi Gerganov
d9779021bd
ggml : add support for ChatGLM RoPE 2023-06-27 00:06:51 +03:00
Georgi Gerganov
c824d2e368
ggml : avoid conv 2d kernel round up 2023-06-26 21:03:59 +03:00
zrm
b853d45601
ggml : add NUMA support (#1556)
* detect NUMA systems and pin work threads to nodes (linux)

* disable mmap prefetch/readahead for NUMA systems

* avoid sending finalize op to thread pool if it does nothing

* silence robot

* fix args

* make --numa a param

* recommendation that n_nodes evenly divide n_threads did not warrant such aggressive enforcement

* lower synchronization overhead

* statically allocate

* move numa state to g_state

* add description for --numa

* ggml : minor style changes

* ggml : minor style + try fix sanitizer build

* llama : allow to initialize backend with NUMA support

* llama : avoid ggml include in llama-util.h

* ggml : style / formatting

* ggml : fix handling of ops with n_threads > n_tasks > 1

* server : utilize numa parameter

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-26 20:57:59 +03:00
Georgi Gerganov
bd34cdde38
ggml : sync latest ggml (custom operators) 2023-06-25 14:25:08 +03:00
Robyn
5ec8dd5a3c
#1869 Fix null reference errors when training from scratch with CUDA (#1907)
* #1869 Fix null reference errors when training from scratch with CUDA build

Calling ggml_compute_forward when node->src0 was null was causing train-text-from-scratch.exe to terminate unexpectedly.

* ggml : do not dereference src0 if NULL

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-24 20:10:29 +02:00
slaren
f2c754e1c3
ggml : improve ggml_graph_dump_dot, add ggml_format_name (#1978)
* Improve ggml_graph_dump_dot, add ggml_format_name

* add more automatic names to view ops

* fix name of copies
2023-06-24 13:57:18 +03:00
Georgi Gerganov
18b35625c3
ggml : fix bug in LBFGS optimizer (found by ggml tests) 2023-06-19 20:43:30 +03:00
Georgi Gerganov
b97ca431db
ggml : sync latest ggml repo (#1924)
* ggml : sync latest ggml repo

* ggml : remove unused comments

* ggml : asserts
2023-06-19 18:12:33 +03:00
l3utterfly
8596af4277
ggml : fix bug in ggml_compute_forward_add_q_f32 (#1918) 2023-06-18 14:19:16 +03:00
Georgi Gerganov
ce2c7d72e2
metal : handle buffers larger than device's maxBufferLength (#1826)
* metal : handle buffers larger than device's maxBufferLength

* metal : print more verbose device info + handle errors

* metal : fix prints for overlapping views

* metal : minimize view overlap to try to utilize device memory better
2023-06-18 09:09:47 +03:00
Borislav Stanimirov
9cbf50c041
build : fix and ignore MSVC warnings (#1889) 2023-06-16 21:23:53 +03:00
Johannes Gäßler
254a7a7a5f
CUDA full GPU acceleration, KV cache in VRAM (#1827)
* Fixed CUDA RoPE

* ggml_cuda_mul_mat_vec_p021

* ggml_cuda_scale

* ggml_cuda_diag_mask_inf

* ggml_is_permuted

* ggml_cuda_cpy

* flatten rows for ggml_cuda_op

* Added a --low-vram option

* Fixed Windows performance

* Fixed LLAMA_CUDA_DMMV_Y > 1 for WizardLM
2023-06-14 19:47:19 +02:00
xaedes
e32089b2c2
train : improved training-from-scratch example (#1652)
* add python wrapper

https://gist.github.com/abetlen/2b90e5f153f6efd00931d098de5c73ce

* fix decoding error. adds errors=ignore parameter

* add python bindings for functions to get and set the whole llama state
(rng, logits, embedding and kv_cache)

* update python bindings

* add text generating baby-llama from scratch example

* fix race condition bug in ggml_compute_forward_diag_mask_f32

* implement ggml_soft_max_back for more performant backward pass of soft_max

avoids creating big intermediate matrices of size n_embd x n_embd for llama layers and n_vocab x n_vocab for cross entropy loss

* improve softmax backward pass

go from quadratic runtime to linear runtime by simplifying the formulas

* 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

* fix bug in ggml_compute_forward_soft_max_back_f32 on DEBUG build

* improve performance of mul_mat backward pass

avoid transpose by using mul_mat with swapped arguments

* avoid printing too much newlines in baby-llama-text

* activate threading in baby-llama-text

* add ggml_out_prod and use it for mul_mat backward pass for improved performance

performance stats report improvement from 37 seconds to 16 seconds runtime during my training tests

* better weight initialization improves training convergence at start

* better weight initialization improves training convergence at start

* improve ggml_out_prod performance

- change iteration order (>15s -> 10s runtime)
- parallelize over one more dimension: over dst matrix rows (10s -> <5s runtime)

* add llama sampler, shuffle samples and constrain sampling to tokens occurring in train data

* fix get_samples call, add model tensor names, increase model size, start training samples after newline

* save train trained model to checkpoint and load model to be trained from checkpoint

* use inplace functions where possible

* initialize rng with srand

* use different arguments for input and output checkpoint

* ggml fixes to support backward pass on inplace operations

* remove duplicate include

* fix cross entropy loss

- add target probabilities for each sample which is then used in cross entropy loss

* print used memory before and after optimization

* sample with non-greedy sampling parameters at the end of training

* add cmake target for baby-llama-text

* add ggml_add1_inplace to header

* enable gradient propagation for inplace add1 and scale operations

those functions backward passes don't need the original src0, so they also work when forward is inplace

* implement AdamW in ggml_opt_adam by adding weight decay parameter (default 0.001f)

also add a schedule parameter (default 1.0f) that can be used to scale alpha and decay according to learning schedule.
setting the decay parameter to zero disables AdamW resulting in normal Adam optimizer.

since the difference between Adam and AdamW is minimal it is not implemented as another optimizer, but integrated into the existing Adam optimizer.

* use inplace operations in cross_entropy_loss

* fix random weight initialization scale

* add missing default parameters for adam optimizer

* add ggml_opt_context, so that we can properly resume training

otherwise the optimizer states, tracking statistics about the error function and its derivates,
will reset to zero each time ggml_opt is called, hindering convergence on resumed training.

now the optimizer context and all its memory is stored in a separate struct.

* fix bug in llama_sample_token_mirostat_v2

when all candidates are filtered out through mu threshold, the following soft_max operation will fail.
so keep at least one.

* add forward function without using cache, for more performant training

during training on whole samples no cache is required.
removing the cache and simplifying the remaining code results in performance and memory usage improvement.

* print suppressed newline tokens as string "\n"

printing too much actual newlines is suppressed to avoid flooding the console.

* store optimizer state in training checkpoint and add learning schedule

persistent optimizer state allows to resume training without resetting the optimizer
learning schedule consists of linear warmup ramp followed by cosine decay with restarts

* remove unused functions

* fix bug in get_samples which corrupted training targets

* save checkpoint only when it was trained

* simplify code

* remove trailing whitespace

* simplify backward pass for SQRT

* replace inefficient repeat backward pass with dedicated repeat_back operation

* add ggml_cross_entropy_loss with backward pass for faster training

cross entropy loss can also be implemented using softmax and log, but as dedicated operation it is faster and especially avoids unnecessary memory overhead.

* add tests for cross_entropy_loss backward pass

finite differences regularly results in estimated gradient of zero, despite the backward pass giving non zero gradient.
_probably_ the finite differences fails due to numerical issues

* use ggml_cross_entropy_loss in text training example

* remove trailing whitespace

* slightly improve how cross entropy loss is compute

btw: directly implemented cross entropy loss seems to have way lower magnitudes than when implemented with softmax and log.
probably the input to log gets closer to zero due to float numerics.
maybe the multiplication by (1.0-eps)/sum is more accurate..

* add llama_get_vocab to get the vocabulary as output parameters

* set default model.type for unknown models with few layers

* add export of training checkpoint to llama compatible model file

* get vocabulary for exporting training checkpoint to llama compatible model file

* implement backward pass of flash attention

* bugfixes for backward pass of flash attention

* test flash attention backward pass

need to set loose error bounds to pass.
the finitie differences are close to numeric limits and often return quite different values than the backward pass.
reducing eps further lets the gradients vanish completely.
likewise setting eps to big results in wronger values.
the softmax in the middle of the function is probably the most responsible for the numeric issues using finite differences.

* add option to train with flash attention and move options to the top of the main function

training from scratch also works with flash attention
training convergence and generation results after fix number of iterations are worse than when not using flash attention.
maybe there still lingers a bug in the flash attention backward pass?
but training works, just with slower convergence.

flash attention is still worth to use, because it requires way less memory and is faster with high n_ctx

* add train_params and command line option parser

* remove unnecessary comments

* add train params to specify memory size

* remove python bindings

* rename baby-llama-text to train-text-from-scratch

* replace auto parameters in lambda function

* add #include <climits>

* add explicit cast to fix compile error

"error: non-constant-expression cannot be narrowed from type 'int64_t' (aka 'long long') to 'uint32_t' (aka 'unsigned int') in initializer list [-Wc++11-narrowing]"

* remove trailing whitespace

* add ggml_opt_resume_g which accepts forward and backward cgraphs

* fix formulas in comments

* bug fix for ggml_compute_forward_get_rows_back_f32

the result should be set to zero, not to whatever data is in opt0

* improve training memory usage with scratch buffers

instead of relying on the automatic backward pass, we manually create the graph for the backward pass.
it turns out that all backward pass operations need only temporary memory which can be reused after each layer.

will compute backward pass for ALL model parameters

* add option to use scratch buffers in training or not

make it configurable because currently training with scratch buffers implies flash attention and optimization over all parameters.

* ci : disable temporary

* store view offset and permute axes in opt[0] instead of storing it in padding

use memcpy to store offset, because offset is of type size_t.
when storing it as int32_t offset would have to be smaller than 2^31 which is not necessarily true.

* minor : fix compile warnings + minor style changes

* fix bug in threaded indices calculation of ggml_compute_forward_flash_attn_back_f32

* store view offset like in master branch

* bug fix in forward_batch_wo_cache_flash_attn_train

* scratch buffer bug fixes in forward_batch_wo_cache_flash_attn_train

data of permute and reshape is the same as their input.
if we want to preserve the output of permute/reshape, we also need to preserve their inputs.

replace reshape(src0, src1) with reshape_nd calls so that we don't need src1.

replace (temporary) t03 with ggml_repeat(ctx0, layer.attention_norm, t02).
in the future we could also use the new broadcasting ggml_mul to avoid these repeat calls.
for this we need backward pass of broadcasting ggml_mul.

* remove unnecessary scratch buffer 0

buf 0 is persistent memory, so we can just disable scratch for this by using buf -1

* avoid creating unnecessary grad tensors

previously we need to create grads for model parameters, so that expand(..) correctly populates cgraph->leafs & cgraph->grads
this wasted memory, because unnecessary grad for each op were automatically created:
the automatically generated grad was unnecessary because we later manually set the grad (e.g. t35->grad = expand(gb, ...) ).
this discarded the automatically generated grad resulting in wasted memory.

improved this by changing expand(..) to not use ggml_build_forward_expand.
expand set cgraph->nodes but not the leafs.
cgraph->leafs & cgraph->grads are set in another pass after the last expand call.

* print used training seed

* zero initialize gfbuf and gbbuf

* ci : re-enable workflows + add README for training

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-06-13 22:04:40 +03:00
Kerfuffle
74d4cfa343
Allow "quantizing" to f16 and f32 (#1787)
* Allow "quantizing" to f16 and f32

Fix an issue where quantizing didn't respect LLAMA_NO_K_QUANTS

Add brief help to the list of quantization types in the quantize tool

Ignore case for quantization type arguments in the quantize tool
2023-06-13 04:23:23 -06:00
Georgi Gerganov
17c10acfb4
ggml : force no_alloc == false when creating opt tensors (close #1699)
This is needed to make operators like ggml_view() be able to store their
parameters in the ggml context's memory and not get discarded when
no_alloc is true
2023-06-10 12:08:15 +03:00
Xingchen Song(宋星辰)
ef3171d162
ggml : workaround for missing _mm256_setr_m128i in GCC < 8 (#1638) 2023-06-10 10:49:40 +03:00
Steven Roussey
b50b570ed9
ggml : fix fprintf warnings (#1720) 2023-06-08 10:12:28 +03:00
Georgi Gerganov
5c64a0952e
k-quants : allow to optionally disable at compile time (#1734)
* k-quants : put behind optional compile flag LLAMA_K_QUANTS

* build : enable k-quants by default
2023-06-07 10:59:52 +03:00
Georgi Gerganov
2a4e41a086
llama : fix compile warnings 2023-06-06 22:41:53 +03:00
Johannes Gäßler
17366df842
Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
* CUDA multi GPU + scratch

ggml_cuda_compute_forward

Tensor parallelism

ggml_cuda_add

ggml_cuda_rms_norm

ggml_cuda_silu

CUDA scratch buffer

--main-gpu CLI option
2023-06-06 21:33:23 +02:00
Georgi Gerganov
2d43387daf
ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710) 2023-06-06 10:18:03 +03:00
kiltyj
9d0693bce3
metal : use shared buffers between CPU and GPU (#1696)
* 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>
2023-06-05 23:24:04 +03:00
grahameth
efe0507632
ggml : fix internal overflow in ggml_time_us on Windows (#1702)
Co-authored-by: grahameth <->
2023-06-05 23:11:49 +03:00
Kawrakow
99009e72f8
ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684)
* 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>
2023-06-05 22:56:18 +03:00
Georgi Gerganov
ecb217db4f
llama : Metal inference (#1642)
* 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 98c267fc77fe811082f672538fc91bcfc9072d63.

* metal : add comments

* metal : clean-up stuff, fix typos

* readme : add Metal instructions

* readme : add example for main
2023-06-04 23:34:30 +03:00
0cc4m
dcb2ed4826
OpenCL: Fix duplication of layers in VRAM and RAM, add GPU mul kernel (#1653)
* 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
2023-06-04 08:12:05 +02:00
Georgi Gerganov
7552ac5863
ggml : sync cgraph import / export API 2023-05-29 19:31:44 +03:00
Georgi Gerganov
5d1830b99d
ggml : fix bug in ggml_alibi 2023-05-29 19:30:49 +03:00
apcameron
a6704643b6
ggml : add support for the RISCV architecture (#1616) 2023-05-27 23:03:25 +03:00
Georgi Gerganov
93618031c7
ggml : add ggml_tensor_overhead() 2023-05-27 16:19:56 +03:00
Georgi Gerganov
bdbda1b17a
ggml : sync ggml core (minor additions, e.g. ggml_get_tensor_by_name()) 2023-05-27 12:23:16 +03:00
0cc4m
2e6cd4b025
OpenCL Token Generation Acceleration (#1459)
* 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>
2023-05-23 00:33:24 +03:00
Georgi Gerganov
265db9834e
ggml : output 3d sizes in ggml_graph_dump_dot() 2023-05-21 11:56:23 +03:00
Georgi Gerganov
fab49c685e
ggml : update WASM SIMD 2023-05-20 20:00:41 +03:00
Georgi Gerganov
3de84b2606
ggml : add ggml_clamp() (#1539)
* ggml : add ggml_clamp()

* ggml : indentation
2023-05-20 15:34:45 +03:00
Johannes Gäßler
affc76edfd
cuda : loading models directly into VRAM, norm calculation on GPU, broadcasting for ggml_mul (#1483)
* 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 2bb2ff1748513591ad45b175a75ed1d8089d84c8.

* 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>
2023-05-20 15:19:28 +03:00
Maxime
503db28849
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>
2023-05-20 10:22:37 +03:00
Georgi Gerganov
4fd3e29297 ggml : fix scalar implementation of Q4_1 dot 2023-05-20 10:13:19 +03:00
Georgi Gerganov
2d5db48371
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
2023-05-19 22:17:18 +03:00
Ilya Kurdyukov
42627421ec
~7% faster Q5_1 AVX2 code (#1477) 2023-05-16 18:36:47 +00:00
xaedes
79b2d5b69d
ggml : alternative fix for race condition bug in non-inplace ggml_compute_forward_diag_mask_f32 (#1454)
* 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>
2023-05-14 18:55:02 +03:00