Commit Graph

10 Commits

Author SHA1 Message Date
Kawrakow
e9b66ee982
metal : add Q4_1 implementation (#1785)
23.3 ms / token, so just ~1% slower than q4_0.
Achieves 290 GB/s memory throughput.

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-06-10 11:28:11 +03:00
AT
92f44ff7f7
metal : add GELU implementation (#1770)
Co-authored-by: Adam Treat <adam@nomic.ai>
2023-06-09 11:00:51 +03:00
Kawrakow
245fc3c37d
metal : faster q4_0 (#1775)
* metal : 8% faster q4_0

Avoid copying into local uchar4 anf float4.

* metal : 17% faster Q4_0

Use 64 threads in a thread group.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-06-09 10:39:59 +03:00
Kawrakow
72ff5282bf
metal : add Q2_K implementation (#1762)
* metal : add Q2_K implementation

27.1 ms / token on M2 Max 30-core GPU, so about the
same speed as Q4_0. Memory throughput is ~156 GB/s.

The access pattern used in the Q2_K
CUDA implementation resulted in significantly lower
performance (~31 ms/token).

* Fixing merge conflicts

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-06-08 22:28:21 +03:00
Kawrakow
0f291e1f65
metal : Q6_K implementation (#1752)
* Metal implementation for Q4_K

Very slow for now:
42 ms / token, Q4_0 runs in 28 ms/token on my
30-core M2 Max GPU.

* Optimizing Q4_K on metal

The first token always takes longer, I guess because
the metal kernel is being jit-compiled.
So, using n = 128 to measure time.

At this point Q4_K takes 29.5 ms / token
compared to 27.2 ms / token for Q4_0.
Quite a bit better than the initial attempt,
but still not good enough.

* Optimizing q4_K metal dot some more

For n = 256 it is now 28.1 ms/token compared to
27 ms/token for q4_0.

* Fix after merge with master

* Metal implementation for Q6_K

Similar to the CUDA implementation.
No idea if this is the optimum for Metal, but the few
alternative variants I tried all had a lower performance.

We get 36.5 ms / token on M2 Max with 30 GPU cores.
This corresponds to ~200 GB/second throughput.

* clang-tidy : add config back

* Much better Q6_K implementation for metal

28.3 ms / token for 7B. Subtracting ~9 ms that is spent in
other compute graph operations, we are left with ~19 ms
for the matrix multiplications. The model is ~5.5 GB,
so we are getting 1000 / 19 * 5.5 = 290 GB/s!

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-06-08 19:46:22 +03:00
Kawrakow
4161bdc04d
metal : add Q4_K implementation (#1733)
* Metal implementation for Q4_K

Very slow for now:
42 ms / token, Q4_0 runs in 28 ms/token on my
30-core M2 Max GPU.

* Optimizing Q4_K on metal

The first token always takes longer, I guess because
the metal kernel is being jit-compiled.
So, using n = 128 to measure time.

At this point Q4_K takes 29.5 ms / token
compared to 27.2 ms / token for Q4_0.
Quite a bit better than the initial attempt,
but still not good enough.

* Optimizing q4_K metal dot some more

For n = 256 it is now 28.1 ms/token compared to
27 ms/token for q4_0.

* Fix after merge with master

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-06-08 10:08:23 +03:00
Georgi Gerganov
44f906e853
metal : add f16 support 2023-06-06 20:21:56 +03:00
Spencer Sutton
590250f7a9
metal : add checks for buffer size (#1706)
Co-authored-by: Spencer Sutton <Spencer.Sutton@precisely.com>
2023-06-06 06:28:17 +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
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 98c267fc77.

* 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