Commit Graph

129 Commits

Author SHA1 Message Date
Georgi Gerganov
ab336a9d5e
code : normalize enum names (#5697)
* coda : normalize enum names

ggml-ci

* code : cont

* code : cont
2024-02-25 12:09:09 +02:00
Kawrakow
4c4cb30736
IQ3_S: a much better alternative to Q3_K (#5676)
* iq4_nl: squash commits for easier rebase

* Basics (quantize, dequantize)
* CUDA dequantize and dot product
* Slightly faster CUDA dot product (120 t/s)
* Switch to 6-bit scales
* Scalar dot product
* AVX2 dot product
* ARM_NEON dot product
* Works on metal, but still slow
* Slightly better Metal dot product
* Another small Metal improvement
* Metal dot product is getting there
* Faster CUDA dot product
* Add 1/8 ffn_down layers as Q5_K when no imatrix has been provided
* Report the actual bpw
* Add _xs mix that is 4.05 bpw for non-MoE models
* Remove IQ4_XS for now, slightly adjust kvalues_iq4nl
* AVX2 dot product uses Q8_0 instead of Q8_K
* Add to test-backend-ops
* Minor fix
* Also use use Q5_K for attn_output in MoE models
* Fixes after merging latest master
* Switching to blocks of 32
* AVX2 for blocks of 32
* Scaler dot product for blocks of 32
* ARM_NEON dot product for blocks of 32
* Metal kernels for blocks of 32
* Slightly faster Metal kernels

* Resurrecting iq3_xs

After all the experimentation, nothing was better than this.

* Minor PPL improvement via a block scale fudge factor

* Minor improvement via 3 neighbours

* iq3_xs: working scalar and AVX2 dot products

* iq3_xs: ARM_NEON dot product - works but extremely slow (10 t/s)

* iq3_xs: working Metal implementation

* Adding IQ3_M - IQ3_XS mix with mostly Q4_K

* iiq3_xs: a 3.4375 bpw variant

* iq3_xs: make CUDA work for new version

* iq3_xs: make scalar and AVX2 work for new version

* iq3_s: make ARM_NEON work with new version

* iq3_xs: make new version work on metal

Performance is very similar to Q3_K_S

* iq3_xs: tiny Metal speed improvement

* iq3_xs: tiny Metal speed improvement

* Fix stupid warning

* Q3_K_XS now uses a mix of IQ3_XS and IQ3_XXS

* iq3_xs: rename to iq3_s

* iq3_s: make tests pass

* Move Q3_K_XS mix to 3.25 bpw

* Attempt to fix failing tests

* Another attempt to fix the Windows builds

* Attempt to fix ROCm

* ROCm again

* iq3_s: partial fix for QK_K = 64

* iq3_s: make it work on metal for QK_K = 64

Pleasent surprise: the coding was super-block size independent,
so all it took was to delete some QK_K == 256 guards.

* Will this fix ROCm?

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-24 16:23:52 +02:00
Kawrakow
a14679cc30
IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)
* iq4_nl: squash commits for easier rebase

* Basics (quantize, dequantize)
* CUDA dequantize and dot product
* Slightly faster CUDA dot product (120 t/s)
* Switch to 6-bit scales
* Scalar dot product
* AVX2 dot product
* ARM_NEON dot product
* Works on metal, but still slow
* Slightly better Metal dot product
* Another small Metal improvement
* Metal dot product is getting there
* Faster CUDA dot product
* Add 1/8 ffn_down layers as Q5_K when no imatrix has been provided
* Report the actual bpw
* Add _xs mix that is 4.05 bpw for non-MoE models
* Remove IQ4_XS for now, slightly adjust kvalues_iq4nl
* AVX2 dot product uses Q8_0 instead of Q8_K
* Add to test-backend-ops
* Minor fix
* Also use use Q5_K for attn_output in MoE models
* Fixes after merging latest master
* Switching to blocks of 32
* AVX2 for blocks of 32
* Scaler dot product for blocks of 32
* ARM_NEON dot product for blocks of 32
* Metal kernels for blocks of 32
* Slightly faster Metal kernels

* iq4_nl: Fix after merging with master

* iq4_nl: another fix after merging with master

* Use IQ4_NL instead of Q4_K when using k-quants is not possible

* Fix typo that makes several tests fail

* It was the ggml_vdotq thing missed inside the brackets

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-21 11:39:52 +02:00
Didzis Gosko
890559ab28 metal : option to embed MSL source into compiled binary (whisper/1842)
* ggml : embed Metal library source (ggml-metal.metal) into binary

enable by setting WHISPER_EMBED_METAL_LIBRARY

* rename the build option

* rename the preprocessor directive

* generate Metal library embedding assembly on-fly during build process
2024-02-19 15:09:43 +02:00
Kawrakow
bd2d4e393b
1.5 bit quantization (#5453)
* iq1_s: WIP basics

* iq1_s: CUDA is working

* iq1_s: scalar CPU dot product

* iq1_s: WIP AVX2 dot product - something is not right

* Fix tests

* Fix shadow warnings

* Fix after merge with latest master

* iq1_s: AVX2 finally works

* iq1_s: ARM_NEON dot product. Works, but not very fast

* iq1_s: better grid

* iq1_s: use IQ2_XXS for attn_output

At a cost of 0.04 extra bpw this gives a big improvement in PPL.

* iq1_s: Metal basics

Dequantize works, but not dot product

* iq1_s: Metal works, but quite slow

As usual, Apple Silicon does not like the code I write.

* iq1_s: Tests

* iq1_s: slightly faster dot product

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-18 18:16:55 +02:00
Georgi Gerganov
8f1be0d42f
ggml : add ALiBi support for ggml_soft_max_ext (#5488)
* ggml : avoid recomputing alibi slopes (CPU)

* llama : reuse hparams.f_max_alibi_bias in all cases

ggml-ci

* ggml : support alibi bias in ggml_soft_max_ext (CPU + Metal)

ggml-ci

* ggml : handle all SRCs (do not break on first null)

ggml-ci

* tests : do not use slope for large soft_max

accumulates too much error

ggml-ci

* ggml : alternative ALiBi without extra tensor

We compute the slopes in the kernel

ggml-ci

* cuda : add ALiBi support in ggml_soft_max_ext

ggml-ci

* ggml : deprecate ggml_alibi

* ggml : support multi-sequence ALiBi (Metal)

ggml-ci

* cuda : add multi-seq ALiBi + remote F16 soft_max

ggml-ci

* ggml : update deprecation message

* ggml : fix pos ptr when no ALiBi

ggml-ci

* cuda : fix performance (pow -> powf)

* cuda : precompute ALiBi constants

* metal : pre-compute ALiBi slopes

ggml-ci

* llama : init kq_pos only if needed

ggml-ci

* test-backend-ops : add null pos test to soft_max

test-backend-ops : replace soft_max tests

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-02-17 23:04:16 +02:00
Ananta Bastola
6e4e973b26
ci : add an option to fail on compile warning (#3952)
* feat(ci): add an option to fail on compile warning

* Update CMakeLists.txt

* minor : fix compile warnings

ggml-ci

* ggml : fix unreachable code warnings

ggml-ci

* ci : disable fatal warnings for windows, ios and tvos

* ggml : fix strncpy warning

* ci : disable fatal warnings for MPI build

* ci : add fatal warnings to ggml-ci

ggml-ci

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-17 23:03:14 +02:00
Ian Bull
f026f8120f
metal : use autoreleasepool to avoid memory leaks (#5437)
There appears to be a known memory leak when using the
`MLTCommandBuffer`. It is suggested to use `@autoreleasepool` in
[1,2]

[1] https://developer.apple.com/forums/thread/662721
[2] https://forums.developer.apple.com/forums/thread/120931

This change-set wraps the `ggml_metal_graph_compute` in a
`@autoreleasepool`.

This commit addresses https://github.com/ggerganov/llama.cpp/issues/5436
2024-02-10 12:53:28 +02:00
Georgi Gerganov
efb7bdbbd0
metal : add im2col F32 dst support (#5132) 2024-01-31 15:35:41 +02:00
Georgi Gerganov
549a1e6cd5
ci : fix yolo URLs + fix metal capture (ggml/712) 2024-01-30 16:20:25 +02:00
Jack Mousseau
5f14ee0b0c
metal : add debug capture backend function (ggml/694)
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-30 16:20:25 +02:00
Kawrakow
f4d7e54974
SOTA 3-bit quants (#5196)
* iq3_xxs: quantize/dequantize

RMSE seems a bit high-ish at about half-way between q2_K and
q3_K, so need to check more.

* iq3_xxs: CUDA dequantize works

* iq2_xxs: tuning quantization

* iq3_xxs: starting to look better

PPL on wiki.test.raw
LLaMA-v1-7B: 6.4218
LLaMA-v2-7B: 6.3560
Mistral-7B : 6.0717

This is better than Q3_K_XS, with a 5% reduction in quantized model
size.

* iq3_xxs: CUDA dot product

We have
PP-512: 5891 t/s
TG-128: 143.9 t/s

* iq3_xxs: scalar and AVX2 dot products

* iq3_xxs: ARM_NEON and Metal

Metal performance is decent, ARM_NEON is pathetic

* iq3_xxs: slightly better grid points

* Faster iq3_xxs and iq2_xs dot products on CUDA

* iq3_xxs: add some quant mix

* iq3_xxs: fix failing quantization test

Dot product still fails. Is this real?

* iq3_xxs: hopefully fix ROCm

* iq3_xxs: failing tests

This time the dot product accuracy did find an actual bug
in the AVX2 implementation.

* Add IQ3_XXS to test-backend-ops

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-30 15:14:12 +02:00
slaren
fbe7dfa53c
ggml : add max buffer sizes to opencl and metal backends (#5181) 2024-01-29 10:05:13 +02:00
Paul Tsochantaris
d2f650cb5b
metal : free metal objects (#5161)
* Releasing MTLFunction references after Metal pipeline construction

* Keeping the `ggml_metal_kernel` structure

* Spacing fix

* Whitespace fix
2024-01-28 21:50:16 +02:00
0cc4m
2307523d32
ggml : add Vulkan backend (#2059)
* Vulkan loader code

* Fix matmul kernel, continue implementation

* Continue implementation

* Vulkan memory management

* Vulkan development

* Matmul call

* Add aligned malloc and free for VMA

* Continue implementation

* First matmul success

* GEMM Kernel optimization

* 1D Blocktiling

* 2D Blocktiling

* Write coalescing

* Continue vulkan implementation and optimization

* First FP16 attempt, disabled for now

* Code abstraction, FP16 implementation, fix kernel, add FP16 to FP32 kernel

* Enable device extensions properly, restore fp16 matmul op

* Fix mulmat_f16

* Output FP32 in fp16 matmul shader

* Fix f16_to_f32 kernel

* dequant_q4_0 kernel

* Add VMA library

* Avoid requesting dedicated memory, VMA can decide that by itself

* Add bounds checking to matmul kernels, improve implementation, fix command buffers not freed properly

* add cmake commands

* Add 2d write operation, profiling code

* Fix 2d write

* Fix queue selection for AMD RADV

* Fix trailing whitespace in vk_mem_alloc.h

* Add WIP warp tile mat mul shaders

* Disable glslc optimization

* Disable glslc optimization for CMake

* Optimize warptile matmul shader, replace blocktile with it

* Add split-k optimization for small matrix multiplication

Use semaphores for synchronization instead of fences or waitidle

Rework async write/read for synchronization

* Fix validation errors, improve compatibility with AMD GPUs

* Rework command buffer handling

* Variable matmul kernel using specialization constants

* Fix synchronization on AMD, add barriers for buffer ownership transfer, add debug flag and prints

* Reuse semaphores

* Handle stage flags during command buffer submission properly

* Increase matmul test runs for consistent results

* Fix F32 matmul

* Add vectorized loading and zeropadding for matrix multiplication

* Use pinned memory for f16 preprocessing

* Don't force aligned matmul

* Don't free before queue done

* Replace VMA library with native Vulkan buffer management

* Basic offloading support with mul_f32 and dmmv for q4_0

* Run glslc commands in parallel

* Unroll loops in dmmv shader

* Reduce usage of waitIdle

* Reuse pinned allocation for f16 conversion

* Handle devices with only a single queue

* Fix trailing whitespace in CMakeLists.txt

* Allow parallel execution of kernels, parallelize third and fourth dimension calls

* Add fallback for devices only supporting one DescriptorSet per DescriptorPool

* Move to graph function similar to CUDA implementation

* Use F16 kernel for most things, replace q_f32 with mul_mat_q_f16 function

* Add F32 dmmv shaders

* Batch submissions

* Add .spv to gitignore

* Split off matrix vector multiplication for separate optimization

* Use single command buffer for matrix vector multiplication ops

* Reduce overhead of mul_f32 calls by using a single command buffer

* Add submission batching to mul_f32

* Fix tests

* Add missing barrier

* Add further missing barrier

* Add further ops

* Replace vk::QueueFamilyIgnored with VK_QUEUE_FAMILY_IGNORED to support more Vulkan header versions

* Remove unnecessary cblas link

* Fix descriptor set pre-allocation assert

* Add runtime shader compilation, start transferring shaders to this approach

* Transfer remaining shaders to header and compile on runtime

* Fix fp32 fallback if device doesn't support fp16, add force disable env var GGML_VULKAN_DISABLE_F16

* Add support for q4_1, q5_0, q5_1 and q8_0

* Remove unnecessary scalar layout extension

* Parse graph early to pre-record command buffers

* Add q6_k support

* Add multi-submit for command buffers

* Fix q6_k dequant shader for AMD

* Fix q6_k for GPUs without fp16 support

* Simplify q6_k fp16 fix

* Minor fixes

* Fix wg_denom of m-mulmat shaders

* Add Python-based Vulkan shader generator

* Replace shaderc dependency with precompiled shaders

Fix python script to generate shaders

* Clean up code

* Fix shader generator script Windows compatibility

Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>

* Close file before deletion

* Fix vulkan shader fp32 name

* Add q2_k and q3_k support

Add validation check to compare shader results to cpu results

* Add q4_k support

* Add q5_k support

* Bake SPIR-V bytecode into the library instead of loading shaders from file

* Switch to signal semaphores for flexibility

Prepare broadcasting support for mul mat

* Finish broadcasting mul mat support for GQA

* Clean up unused functions

Add repeat op

* Add further ops, not yet enabled. Improve semaphore code

* Reduce number of used semaphores by utilizing timelines more properly

* Remove queue information

* Reuse timeline semaphores, allow parallel operation with binary semaphores to work around nvidia driver limitations

* Add Vulkan to llama-bench

* Remove cblas dependency

* Fix matmul k-split bug

* Fix q4_k dmmv K_QUANTS_PER_ITERATION 1 shader

* Add RMS Norm shader, rework op_f32 shader setup, fix matmul bug

* Fix issues with float16 overflows in shaders

* Fix issues with older Vulkan headers on Ubuntu 22.04

* Allow multi-op partial offloading by parsing the graph to preallocate enough between-op buffers

* Implement further ops, rework op_f32 calls, fix bugs

* Finish full offloading support, add last remaining ops, fix bugs, remove redundant code

* Upload generated file ggml-vulkan-shaders.hpp, remove redundant shaders

* Merge upstream changes, fix conflicts, adapt soft_max op

* Fix Python and shader header format

* Free model gpu buffers on exit

* Use single queue per device to simplify code

* Add matmul shader support for running multiple calculations in parallel

* Switch from semaphore-synchronized multiple command buffers per op to single command buffer for multiple ops, whole graph if possible

* Fix missing event cast

* Replace uint64_t(-1) with UINT64_MAX, rename function for clarity

* Fix warning about empty C function parameters

* Fix compiler warnings

* Properly implement Vulkan backend buffer handling

* Fix oversized host staging buffers

* Simplify barrier synchronization calls

* Fix gcc warnings

* Implement max_size for backend buffer types to limit the size of a single allocation

* Use min of maxMemoryAllocationSize and maxBufferSize for device max allocation size

* refactor multi buf

* Disable unsupported ops to fix tests

* Check for maintenance4 support before using it

* Handle devices with only a single queue

* Fix single queue logic

* propagate buffer usage in multi buffers

* Implement rope_neox op

* Cleanup header and other files

* Simplify gpu_extras by removing events and putting staging memcpys into contexts

* Move queue into context

Add not-yet-enabled async backend ops

* Simplify context use, optimize matmul shader for warp size 64 (AMD GCN), fix split_k matmul shader optimization

* Add get_max_size to SYCL backend.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* llama : fix trailing whitespace

---------

Co-authored-by: Henri Vasserman <henv@hot.ee>
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-28 19:03:59 +02:00
Paul Tsochantaris
6dd3c28c9c
metal : remove unused n_buffers and buffers (#5129) 2024-01-26 14:16:07 +02:00
Georgi Gerganov
ddc5a5033f
metal : show compile log messages 2024-01-25 11:26:17 +02:00
Georgi Gerganov
26d607608d
metal : disable support for MUL_MAT F32 x F16 2024-01-23 15:50:56 +02:00
Paul Tsochantaris
1e605f4102
metal : fix memory leak, dangling pointer and unused autorel (#5007)
* Metal memory: Small memory leak on init, dangling pointer, and unused autorelease pool in graph compute

* SPM header potential fix

* Reverting symlinks
2024-01-18 10:47:24 +02:00
Georgi Gerganov
c918fe8dca
metal : create autorelease pool during library build (#4970)
* metal : create autorelease pool during library build

ggml-ci

* test : simplify

ggml-ci
2024-01-17 18:38:39 +02:00
Paul Tsochantaris
7563293665
metal : remove unnecessary nil check (#4986) 2024-01-17 10:07:24 +02:00
Paul Tsochantaris
158f8c9e21
metal : localized logic in ggml_metal_graph_compute (#4924)
* Metal: Localized logic in `ggml_metal_graph_compute`, minor performance improvement

* Whitespace

* Collecting command buffer completions on single thread

* Whitespace

* Reduce diff noise
2024-01-16 19:05:19 +02:00
Alex Azarov
3a48d558a6
metal : replace loop of dispatch_async with dispatch_apply (#4934)
* Replace loop of dispatch_async with dispatch_apply

* Update ggml-metal.m

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-16 15:41:27 +02:00
Alex Azarov
7c8d3abd1a
metal : log recommendedMaxWorkingSetSize on iOS 16+ (#4936)
* metal: Log `recommendedMaxWorkingSetSize` on iOS 16+

* Only log on iOS and macOS, ignoring tvOS and other platforms

* Check for Xcode version before using recommendedMaxWorkingSetSize

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-16 15:33:02 +02:00
Justine Tunney
a0b3ac8c48
ggml : introduce GGML_CALL function annotation (#4850)
This change makes it possible to build ggml-cuda.cu and ggml-metal.m as
independent dynamic shared objects, that may be conditionally linked at
runtime in a multiplatform binary. It introduces a GGML_CALL annotation
that documents which functions have a cyclic call relationship, between
the application code and GPU modules.

This change does nothing, unless the build defines -DGGML_MULTIPLATFORM
which causes back-references and function pointers to conform to MS ABI
which is supported by NVCC, ROCm, XCode, GCC and Clang across platforms
2024-01-16 13:16:33 +02:00
Alex Azarov
5f5fe1bd60
metal : correctly set SIMD support flags on iOS (#4923)
* Correctly set support_simdgroup_reduction and support_simdgroup_mm on iPhone/iPad

* log a little bit more info on iOS
2024-01-14 10:44:39 +02:00
Georgi Gerganov
4be5ef556d
metal : remove old API (#4919)
ggml-ci
2024-01-13 20:45:45 +02:00
Georgi Gerganov
2d57de5255
metal : disable log for loaded kernels (#4794) 2024-01-13 18:46:37 +02:00
Georgi Gerganov
b38b5e93ae
metal : refactor kernel loading code (#4794)
* metal : detect more GPU families

* metal : refactor kernel loading

* metal : set kernel family requirements

* metal : fix kernel init + fix compile options

* metal : take into account simdgroup reduction support

* metal : print only skipped kernels

* metal : fix check for simdgroup reduction support

* metal : check for Metal 3

* metal : free allocations

* metal : normalize encoder:setComputePipelineStatus calls

ggml-ci

* metal : fix Metal3 family check

ggml-ci

* metal : check for simdgroup matrix mul. feature

ggml-ci
2024-01-13 18:03:45 +02:00
slaren
e7e4df031b
llama : ggml-backend integration (#4766)
* llama : ggml-backend integration

* ggml-backend : add names to buffers

* fix unmap after loading

* batched-bench : add tensor_split param

* llama : check for null tensor_split

* ggml-backend : increase GGML_MAX_BACKENDS

* improve graph splitting, partial fix for --no-kv-offload

* cuda : add ggml-backend split buffer support

* cuda : do not create buffer types for devices that don't exist (fixes usage without CUDA devices available)

* ggml : fix null backend dereference (#4807)

* ggml : fix null backend dereference

* ggml : also check ggml_backend_is_cpu

* test-backend-ops : check buffer allocation failures

* llama : add cparam (split_mode) and command line argument (--split-mode, -sm) to configure the split mode (none, layer or row)

* ggml : fix mul_mat_id work size

* llama : rewrite session kv load/set without graphs

* minor

* llama : only initialize used backends, free backends on context free

* llama : abort ctx if cuda backend init fails

* llama : rewrite lora with ggml-backend and compute on CPU

ggml-ci

* llama : only map to a backend buffer the region of the file mapping containing the tensors used in the buffer

* opencl : add ggml-backend buffer type

* cuda : only use batched_cublas with batched mat muls (fixes fp16 tg perf)

* llama : on Metal, by default offload the full model

ggml-ci

* metal : page align the data ptr (#4854)

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* cuda : fix split buffer free

* address review comments

* llama-bench : add split-mode parameter

* fix whitespace

* opencl : fix double initialization

* server : add --split-mode parameter

* use async copy and compute to improve multi-gpu performance

ggml-ci

* use async memcpys to copy the graph outputs to the CPU

* fix opencl

* use a host buffer for the cpu compute buffer for faster copies to the gpu

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2024-01-12 20:07:38 +01:00
Kawrakow
49662cbed3
ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)
* iq2_xs: basics

* iq2_xs: this should have been in the basics

* iq2_xs: CUDA and scalar CPU works

* iq2_xs: WIP Metal

* iq2_xs: Metal now works

* iq2_xs: working, but dog slow, ARM_NEON dot product

* iq2_xs: better ARM_NEON dot product

We are now at 19.5 t/s for TG-128 and 61 t/s for PP-512 when
running on the CPU.

* iq2_xs: AVX2 dot product - 19.5 t/s

* iq2_xs: faster AVX2 dit product

21.4 t/s for TG-128, 59.2 t/s for PP-512.
The latter is 2x compared to the previous version.

* iq2_xs: had forgotten to delete iq2-data.h

* Add llama enum for IQ2_XS

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-11 21:39:39 +02:00
Paul Tsochantaris
2a7c94db5f
metal : put encoder debug group behind a define (#4873) 2024-01-11 16:31:52 +02:00
Georgi Gerganov
3267c2abc7
metal : fix deprecation warning (ggml/690) 2024-01-11 09:39:05 +02:00
Jack Mousseau
5362e43962
metal : wrap each operation in debug group (ggml/690) 2024-01-11 09:39:05 +02:00
Kawrakow
dd5ae06405
SOTA 2-bit quants (#4773)
* iq2_xxs: basics

* iq2_xxs: scalar and AVX2 dot products

Needed to change Q8_K to have quants in the -127...127 range,
else the IQ2_XXS AVX implementation becomes very awkward.
The alternative would have been to use Q8_0 instead. Perhaps
I'll change later, for now this is what we have.

* iq2_xxs: ARM_NEON dot product

Somehow strangely slow (112 ms/token).

* iq2_xxs: WIP Metal

Dequantize works, something is still wrong with the
dot product.

* iq2_xxs: Metal dot product now works

We have
PP-512 = 475 t/s
TG-128 = 47.3 t/s

Not the greatest performance, but not complete garbage either.

* iq2_xxs: slighty faster dot product

TG-128 is now 48.4 t/s

* iq2_xxs: slighty faster dot product

TG-128 is now 50.9 t/s

* iq2_xxs: even faster Metal dot product

TG-128 is now 54.1 t/s.

Strangely enough, putting the signs lookup table
into shared memory has a bigger impact than the
grid values being in shared memory.

* iq2_xxs: dequantize CUDA kernel - fix conflict with master

* iq2_xxs: quantized CUDA dot product (MMVQ)

We get TG-128 = 153.1 t/s

* iq2_xxs: slightly faster CUDA dot product

TG-128 is now at 155.1 t/s.

* iq2_xxs: add to llama ftype enum

* iq2_xxs: fix MoE on Metal

* Fix missing MMQ ops when on hipBLAS

I had put the ggml_supports_mmq call at the wrong place.

* Fix bug in qequantize_row_iq2_xxs

The 0.25f factor was missing.
Great detective work by @ggerganov!

* Fixing tests

* PR suggestion

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-08 16:02:32 +01:00
Georgi Gerganov
91d38876df metal : switch back to default.metallib (ggml/681)
ggml-ci
2024-01-05 18:02:06 +02:00
Finn Voorhees
1bf681f90e ggml : add error handling to graph_compute (whisper/1714) 2024-01-05 18:02:06 +02:00
Georgi Gerganov
289313716f metal : add kernel_get_rows_i32
ggml-ci
2024-01-03 14:38:38 +02:00
Georgi Gerganov
f3f62f0d83
metal : optimize ggml_mul_mat_id (faster Mixtral PP) (#4725)
* ggml : disable fast-math for Metal (cmake build only)

ggml-ci

* metal : fix Metal API debug warnings

* cmake : add -fno-inline for Metal build (#4545)

* metal : fix API debug warnings

* metal : fix compile warnings

* metal : use uint64_t for strides

* cmake : rename option to LLAMA_METAL_SHADER_DEBUG

* metal : fix mat-vec Q8_0 kernel for BS > 1

* metal : normalize mat-vec kernel signatures

* cmake : respect LLAMA_QKK_64 option

* metal : fix mat-vec Q4_K kernel for QK_K == 64

* metal : optimizing ggml_mul_mat_id (wip)

* metal : minor fix

* metal : opt mul_mm_id
2024-01-02 21:07:47 +02:00
Georgi Gerganov
58ba655af0
metal : enable shader debugging (cmake option) (#4705)
* ggml : disable fast-math for Metal (cmake build only)

ggml-ci

* metal : fix Metal API debug warnings

* cmake : add -fno-inline for Metal build (#4545)

* metal : fix API debug warnings

* metal : fix compile warnings

* metal : use uint64_t for strides

* cmake : rename option to LLAMA_METAL_SHADER_DEBUG

* metal : fix mat-vec Q8_0 kernel for BS > 1

* metal : normalize mat-vec kernel signatures

* cmake : respect LLAMA_QKK_64 option

* metal : fix mat-vec Q4_K kernel for QK_K == 64

ggml-ci
2024-01-02 10:57:44 +02:00
Georgi Gerganov
afefa319f1
ggml : change ggml_scale to take a float instead of tensor (#4573)
* ggml : change ggml_scale to take a float instead of tensor

* ggml : fix CPU implementation

* tests : fix test-grad0

ggml-ci
2023-12-21 23:20:49 +02:00
slaren
d232aca5a7
llama : initial ggml-backend integration (#4520)
* llama : initial ggml-backend integration

* add ggml-metal

* cuda backend can be used though ggml-backend with LLAMA_GGML_BACKEND_CUDA_TEST
access all tensor data with ggml_backend_tensor_get/set

* add ggml_backend_buffer_clear
zero-init KV cache buffer

* add ggml_backend_buffer_is_hos, used to avoid copies if possible when accesing tensor data

* disable gpu backends with ngl 0

* more accurate mlock

* unmap offloaded part of the model

* use posix_fadvise64(.., POSIX_FADV_SEQUENTIAL) to improve performance with mmap

* update quantize and lora

* update session copy/set to use ggml-backend

ggml-ci

* use posix_fadvise instead of posix_fadvise64

* ggml_backend_alloc_ctx_tensors_from_buft : remove old print

* llama_mmap::align_offset : use pointers instead of references for out parameters

* restore progress_callback behavior

* move final progress_callback call to load_all_data

* cuda : fix fprintf format string (minor)

* do not offload scales

* llama_mmap : avoid unmapping the same fragments again in the destructor

* remove unnecessary unmap

* metal : add default log function that prints to stderr, cleanup code

ggml-ci

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-21 21:07:46 +01:00
Georgi Gerganov
4d98d9a656
sync : ggml (SD ops, tests, kernels) (#4444)
* sync : ggml (SD ops, tests, kernels)

ggml-ci

* cuda : restore im2col

ggml-ci

* metal : fix accuracy of dequantization kernels

ggml-ci

* cuda : restore correct im2col

ggml-ci

* metal : try to fix moe test by reducing expert size

ggml-ci

* cuda : fix bin bcast when src1 and dst have different types

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-12-13 21:54:54 +02:00
slaren
799a1cb13b
llama : add Mixtral support (#4406)
* convert : support Mixtral as LLAMA arch

* convert : fix n_ff typo

* llama : model loading

* ggml : sync latest ggml_mul_mat_id

* llama : update graph to support MoE

* llama : fix cur -> cur_expert

* llama : first working version

* llama : fix expert weighting in the FFN

* ggml : ggml_get_rows support 2D indexing [n_tokens, n_experts] (cpu only)

* ggml : add n_as argument to ggml_mul_mat_id

* ggml : fix ggml_get_rows to take into account ne02 / ne11

* metal : add more general support for ggml_get_rows + tests

* llama : add basic support for offloading moe with CUDA

* metal : add/mul/div use general kernel when src1 not cont

* metal : reduce the kernel launches for ggml_mul_mat_id

* ggml : get_rows : support non-contiguos tensors with gaps, generalize up to 3D

* ggml : update get_rows f16 and q

* cuda : support non-contiguous src1 in get_rows

* llama : offload missing ffn_moe_silu

* metal : fix ggml_get_rows to work with non-cont src1

* metal : add indirect mat-vec kernels for all quantization types

* llama : do not quantize expert gating tensors

* llama : add n_expert and n_expert_used to hparams + change quants

* test-backend-ops : add moe test

* cuda : fix get_rows when ncols is odd

* convert : determine n_ctx correctly

* metal : fix ggml_mul_mat_id for F32

* test-backend-ops : make experts more evenly probable (test_moe)

* test-backend-ops : cleanup, add moe test for batches

* test-backend-ops : add cpy from f32 -> all types test

* test-backend-ops : fix dequantize block offset

* llama : fix hard-coded number of experts

* test-backend-ops : simplify and disable slow tests to avoid CI timeout

* test-backend-ops : disable MOE test with thread sanitizer

* cuda : fix mul_mat_id with multi gpu

* convert : use 1e6 rope_freq_base for mixtral

* convert : fix style

* convert : support safetensors format

* gguf-py : bump version

* metal : add cpy f16 -> f32 kernel

* metal : fix binary ops for ne10 % 4 != 0

* test-backend-ops : add one more sum_rows test

* ggml : do not use BLAS with ggml_mul_mat_id

* convert-hf : support for mixtral-instruct (#4428)

* convert : typo fix, add additional hyperparameters, use LLaMA arch for Mixtral-instruct

* convert : use sentencepiece tokenizer for Mixtral-instruct

* convert : make flake8 happy

* metal : fix soft_max kernels

ref: 1914017863

* metal : limit kernels to not use more than the allowed threads

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Radek Pilar <github@mrkva.eu>
2023-12-13 14:04:25 +02:00
Georgi Gerganov
fe680e3d10
sync : ggml (new ops, tests, backend, etc.) (#4359)
* sync : ggml (part 1)

* sync : ggml (part 2, CUDA)

* sync : ggml (part 3, Metal)

* ggml : build fixes

ggml-ci

* cuda : restore lost changes

* cuda : restore lost changes (StableLM rope)

* cmake : enable separable compilation for CUDA

ggml-ci

* ggml-cuda : remove device side dequantize

* Revert "cmake : enable separable compilation for CUDA"

This reverts commit 09e35d04b1.

* cuda : remove assert for rope

* tests : add test-backend-ops

* ggml : fix bug in ggml_concat

* ggml : restore `ggml_get_n_tasks()` logic in `ggml_graph_plan()`

* ci : try to fix macOS

* ggml-backend : remove backend self-registration

* ci : disable Metal for macOS cmake build

ggml-ci

* metal : fix "supports family" call

* metal : fix assert

* metal : print resource path

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-12-07 22:26:54 +02:00
Georgi Gerganov
bcc0eb4591
llama : per-layer KV cache + quantum K cache (#4309)
* per-layer KV

* remove unnecessary copies

* less code duplication, offload k and v separately

* llama : offload KV cache per-layer

* llama : offload K shift tensors

* llama : offload for rest of the model arches

* llama : enable offload debug temporarily

* llama : keep the KV related layers on the device

* llama : remove mirrors, perform Device -> Host when partial offload

* common : add command-line arg to disable KV cache offloading

* llama : update session save/load

* llama : support quantum K cache (#4312)

* llama : support quantum K cache (wip)

* metal : add F32 -> Q8_0 copy kernel

* cuda : add F32 -> Q8_0 copy kernel

ggml-ci

* cuda : use mmv kernel for quantum cache ops

* llama : pass KV cache type through API

* llama : fix build

ggml-ci

* metal : add F32 -> Q4_0 copy kernel

* metal : add F32 -> Q4_1 copy kernel

* cuda : wip

* cuda : add F32 -> Q4_0 and F32 -> Q4_1 copy kernels

* llama-bench : support type_k/type_v

* metal : use mm kernel only for quantum KV cache

* cuda : add comment

* llama : remove memory_f16 and kv_f16 flags

---------

Co-authored-by: slaren <slarengh@gmail.com>

* readme : add API change notice

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-12-07 13:03:17 +02:00
Georgi Gerganov
d7b800b8bc
llama : pad KV cache size (#4280)
* llama : pad KV cache size to 32

* metal : try to improve batched decoding
2023-12-03 10:58:16 +02:00
Georgi Gerganov
ef47ec18da
ggml : add ggml_soft_max_ext (#4256)
* metal : implement soft_max_ext

* cuda : implement soft_max_ext

* ggml : implement soft_max_ext (CPU)

* batched-bench : print threads

ggml-ci

* metal : simplify soft_max encoding

ggml-ci

* cuda : use 512 threads for soft_max instead of 32

* ggml : update soft max cpu

* cuda : do warp-based block reduce

* cuda : increase max block size to 1024

* cuda : fix warp reduction initialization of shared mem

* metal : warp-based reduction for soft max kernel

* metal : warp-based reduce for rms_norm

* metal : simplify soft max kernel

ggml-ci

* alloc : fix build with debug
2023-12-01 10:51:24 +02:00
Xiao-Yong Jin
22da05536f
metal : fix yarn (#4220)
get the correct n_orig_ctx in metal
2023-11-26 10:30:02 +02:00
Georgi Gerganov
4f447a4833
llama : fix data units (#4101)
* llama : fix data units

ggml-ci

* Revert "llama : fix data units"

This reverts commit f5feac831f.

* llama : disambiguate data units

ggml-ci
2023-11-17 10:00:15 +02:00