Commit Graph

158 Commits

Author SHA1 Message Date
slaren
dc68f0054c
cuda : fix vmm pool with multi GPU (#4620)
* cuda : fix vmm pool with multi GPU

* hip

* use recommended granularity instead of minimum

* better error checking

* fix mixtral

* use cudaMemcpy3DPeerAsync

* use cuda_pool_alloc in ggml_cuda_op_mul_mat

* consolidate error checking in ggml_cuda_set_device

* remove unnecessary inlines

ggml-ci

* style fixes

* only use vmm for the main device

* fix scratch buffer size, re-enable vmm pool for all devices

* remove unnecessary check id != g_main_device
2023-12-26 21:23:59 +01:00
FantasyGmm
77465dad48
Fix new CUDA10 compilation errors (#4635) 2023-12-26 11:38:36 +01:00
slaren
5bf3953d7e
cuda : improve cuda pool efficiency using virtual memory (#4606)
* cuda : improve cuda pool efficiency using virtual memory

* fix mixtral

* fix cmake build

* check for vmm support, disable for hip

ggml-ci

* fix hip build

* clarify granularity

* move all caps to g_device_caps

* refactor error checking

* add cuda_pool_alloc, refactor most pool allocations

ggml-ci

* fix hip build

* CUBLAS_TF32_TENSOR_OP_MATH is not a macro

* more hip crap

* llama : fix msvc warnings

* ggml : fix msvc warnings

* minor

* minor

* cuda : fallback to CPU on host buffer alloc fail

* Update ggml-cuda.cu

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

* Update ggml-cuda.cu

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

* ensure allocations are always aligned

* act_size -> actual_size

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2023-12-24 14:34:22 +01:00
slaren
708e179e85
fallback to CPU buffer if host buffer alloc fails (#4610) 2023-12-23 16:10:51 +01:00
Johannes Gäßler
e0a4002273
CUDA: fixed row rounding for 0 tensor splits (#4594) 2023-12-23 09:16:33 +01:00
Georgi Gerganov
ba66175132
sync : ggml (fix im2col) (#4591)
* cuda : fix im2col_f32_f16 (ggml/#658)

ggml-ci

* ggml-alloc : fix ggml_tallocr_is_own

---------

Co-authored-by: leejet <leejet714@gmail.com>
2023-12-22 17:53:43 +02:00
FantasyGmm
a55876955b
cuda : fix jetson compile error (#4560)
* fix old jetson compile error

* Update Makefile

* update jetson detect and cuda version detect

* update cuda marco define

* update makefile and cuda,fix some issue

* Update README.md

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

* Update Makefile

* Update README.md

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-22 17:11:12 +02:00
Henrik Forstén
6724ef1657
Fix CudaMemcpy direction (#4599) 2023-12-22 14:34:05 +01:00
slaren
48b7ff193e
llama : fix platforms without mmap (#4578)
* llama : fix platforms without mmap

* win32 : limit prefetch size to the file size

* fix win32 error clobber, unnecessary std::string in std::runtime_error
2023-12-22 13:12:53 +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
Erik Garrison
0f630fbc92
cuda : ROCm AMD Unified Memory Architecture (UMA) handling (#4449)
* AMD ROCm: handle UMA memory VRAM expansions

This resolves #2797 by allowing ROCm AMD GPU users with a UMA to
dynamically expand the VRAM allocated to the GPU.

Without this, AMD ROCm users with shared CPU/GPU memory usually are
stuck with the BIOS-set (or fixed) framebuffer VRAM, making it
impossible to load more than 1-2 layers.

Note that the model is duplicated in RAM because it's loaded once for
the CPU and then copied into a second set of allocations that are
managed by the HIP UMA system. We can fix this later.

* clarify build process for ROCm on linux with cmake

* avoid using deprecated ROCm hipMallocHost

* keep simplifying the change required for UMA

* cmake: enable UMA-compatible allocation when LLAMA_HIP_UMA=ON
2023-12-21 21:45:32 +02:00
arlo-phoenix
562cf222b5
ggml-cuda: Fix HIP build by adding define for __trap (#4569)
Regression of 1398823922
HIP doesn't have trap, only abort
2023-12-21 20:13:25 +01:00
Johannes Gäßler
9154494808
CUDA: mul_mat_id always on GPU for batches >= 32 (#4553) 2023-12-21 18:42:59 +01:00
bobqianic
66f35a2f48
cuda : better error message for ggml_get_rows (#4561)
* Update ggml-cuda.cu

* Update ggml-cuda.cu

* Update ggml-cuda.cu

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-21 19:06:44 +02:00
slaren
1398823922
cuda : replace asserts in wrong architecture checks with __trap (#4556)
* cuda : replace asserts in wrong architecture checks with __trap

* make bad_arch noreturn, remove returns
2023-12-21 18:02:30 +01:00
LoganDark
1d7a1912ce
Fix access violation in ggml_cuda_free_data if tensor->extra is NULL (#4554) 2023-12-21 10:59:27 +01:00
Johannes Gäßler
799fc22689
CUDA: Faster Mixtral prompt processing (#4538)
* CUDA: make MoE tensors contiguous for batch size>1

* Update ggml-cuda.cu

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

---------

Co-authored-by: slaren <slarengh@gmail.com>
2023-12-20 15:41:22 +01:00
arlo-phoenix
a7aee47b98
ggml-cuda: Fix HIP build (#4528)
regression of #4490
Adds defines for two new datatypes
cublasComputeType_t, cudaDataType_t.

Currently using deprecated hipblasDatatype_t since newer ones very recent.
2023-12-18 22:33:45 +01:00
Ebey Abraham
b9e74f9bca
llama : add phi-2 + fix NeoX rope + ggml_mul_mat_set_prec (#4490)
* phi2 implementation

* fix breaking change

* phi-2 : various fixes

* phi-2 : use layer norm eps

* py : whitespaces

* llama : fix meta KV override bug

* convert : phi don't add BOS token

* convert : revert "added_tokens_decoder" change

* phi-2 : scale Q instead of KQ for better precision

* ggml : fix NeoX rope to rotate just first n_dims

* cuda : less diff in the rope_neox kernel

* ggml : add ggml_mul_mat_set_prec

ggml-ci

* Update ggml-cuda.cu

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

* Update ggml-cuda.cu

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

* cuda : ggml_cuda_op_mul_mat_cublas support F32 precision

* cuda : remove oboslete comment

---------

Co-authored-by: Ebey Abraham <ebeyabraham@microsoft.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
2023-12-18 19:27:47 +02:00
slaren
6744dbe924
ggml : use ggml_row_size where possible (#4472)
* ggml : use ggml_row_size where possible

ggml-ci

* ggml : move ggml_nbytes_split to ggml-cuda.cu
2023-12-14 20:05:21 +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
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
slaren
8a052c131e
ggml-cuda : support stablelm rope (#4156)
* ggml-cuda : support stablelm rope

* remove unused freq_base kernel parameter

* add n_dims parameter to llm_build_k_shift, default to n_rot via overload

* llama : fix llm_build_k_shift args

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-11-24 18:04:31 +01:00
Haohui Mai
55978ce09b
Fix incorrect format strings and uninitialized variables. (#4133)
* Fix incorrect format strings and uninitialized variables.

* Address comments

* Add the missing include statement
2023-11-23 22:56:53 +01:00
Kerfuffle
2923f17f6f
Clean up ggml-cuda.cu warnings when compiling with clang (for ROCM) (#4124)
* ggml-cuda.cu: Clean up warnings when compiling with clang

* ggml-cuda.cu: Move static items into anonymous namespace

* ggml-cuda.cu: Fix use of namespace start macro

* Revert "ggml-cuda.cu: Fix use of namespace start macro"

This reverts commit 26c1149026.

* Revert "ggml-cuda.cu: Move static items into anonymous namespace"

This reverts commit e29757e0f7.
2023-11-18 08:11:18 -07:00
Andrew Godfrey
b83e149ec6
cuda : get_row_rounding F32 (#4095)
* Fix #4017

* Update ggml-cuda.cu

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update ggml-cuda.cu

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2023-11-17 10:01:15 +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
slaren
1cf2850d52
ggml-cuda : increase max graph size (#4084) 2023-11-15 14:58:13 +02:00
Georgi Gerganov
3d68f364f1
ggml : sync (im2col, GPU conv, 32-bit arm compat) (#4060)
ggml-ci
2023-11-13 16:55:52 +02:00
Georgi Gerganov
4760e7cc0b
sync : ggml (backend v2) (#3912)
* sync : ggml (backend v2) (wip)

* sync : migrate examples and llama.cpp to dynamic graphs (wip)

* sync : update tests + fix max op params to 64

ggml-ci

* sync : ggml-cuda

ggml-ci

* llama : fix save/load state context size

ggml-ci

* sync : try to fix build on tvOS

* sync : pass custom graph sizes in training examples

* sync : update graph copies to new ggml API

* sync : update sync-ggml.sh with new files

* scripts : fix header in sync script

* train : fix context size calculations

* llama : increase inference graph size up to 4096 nodes

* train : allocate grads for backward graphs

* train : allocate grads for gb_tmp
2023-11-13 14:16:23 +02:00
Kerfuffle
bb50a792ec
Add ReLU and SQR CUDA ops to (partially) fix Persimmon offloading (#4041)
* Add ReLU and SQR CUDA ops to fix Persimmon offloading

* Persimmon loader: More helpful error on CUDA/ROCM when offloading too many layers
2023-11-13 01:58:15 -07:00
Meng Zhang
46876d2a2c
cuda : supports running on CPU for GGML_USE_CUBLAS=ON build (#3946)
* protyping the idea that supports running on CPU for a GGML_USE_CUBLAS=on build

* doc: add comments to ggml_cublas_loaded()

* fix defined(...)
2023-11-07 08:49:08 +02:00
slaren
2833a6f63c
ggml-cuda : fix f16 mul mat (#3961)
* ggml-cuda : fix f16 mul mat

ggml-ci

* silence common.cpp warning (bonus)
2023-11-05 18:45:16 +01:00
Jared Van Bortel
132d25b8a6
cuda : fix disabling device with --tensor-split 1,0 (#3951)
Co-authored-by: slaren <slarengh@gmail.com>
2023-11-05 10:08:57 -05:00
slaren
48ade94538
cuda : revert CUDA pool stuff (#3944)
* Revert "cuda : add ROCM aliases for CUDA pool stuff (#3918)"

This reverts commit 629f917cd6.

* Revert "cuda : use CUDA memory pool with async memory allocation/deallocation when available (#3903)"

This reverts commit d6069051de.

ggml-ci
2023-11-05 09:12:13 +02:00
slaren
abb77e7319
ggml-cuda : move row numbers to x grid dim in mmv kernels (#3921) 2023-11-03 12:13:09 +01:00
Kerfuffle
629f917cd6
cuda : add ROCM aliases for CUDA pool stuff (#3918) 2023-11-02 21:58:22 +02:00
Georgi Gerganov
c7743fe1c1
cuda : fix const ptrs warning causing ROCm build issues (#3913) 2023-11-02 20:32:11 +02:00
Oleksii Maryshchenko
d6069051de
cuda : use CUDA memory pool with async memory allocation/deallocation when available (#3903)
* Using cuda memory pools for async alloc/dealloc.

* If cuda device doesnt support memory pool than use old implementation.

* Removed redundant cublasSetStream

---------

Co-authored-by: Oleksii Maryshchenko <omaryshchenko@dtis.com>
2023-11-02 19:10:39 +02:00
Georgi Gerganov
4d719a6d4e
cuda : check if this fixes Pascal card regression (#3882) 2023-11-02 08:35:10 +02:00
cebtenzzre
2fffa0d61f
cuda : fix RoPE after #2268 (#3897) 2023-11-02 07:49:44 +02:00
slaren
d02e98cde0
ggml-cuda : compute ptrs for cublasGemmBatchedEx in a kernel (#3891)
* ggml-cuda : compute ptrs for cublasGemmBatchedEx in a kernel

* fix warnings
2023-11-01 23:10:09 +01:00
cebtenzzre
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
Co-authored-by: Jeffrey Quesnelle <jquesnelle@gmail.com>
2023-11-01 18:04:33 -04:00
Andrew Godfrey
73bdcb395e
finetune : add -ngl parameter (#3762)
* Add '-ngl' support to finetune.cpp

* Add fprintf in ggml_cuda_op_add

When I tried CUDA offloading during finetuning following the readme, I got an assert here.
This probably isn't an important case because inference later gives a warning saying you should use f16 or f32 instead when using lora

* Add 'finetune.sh', which currently fails when using GPU

"error: operator (): Finetuning on tensors with type 'f16' is not yet supported"

* tweak finetune.sh

* Suppress some warnings in ggml.c

* Add f16 implementation to ggml_compute_forward_add_f16_f32

* Add an f16 case to ggml_add_cast_impl and llama_build_lora_finetune_graphs

* finetune.sh: Edit comments

* Add "add_f16_f32_f32_cuda"

* Tweak an error message

* finetune.sh: Add an optional LLAMA_MODEL_DIR variable

* finetune.sh: Add an optional LLAMA_TRAINING_DIR variable

* train : minor

* tabs to spaces

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
2023-11-01 13:49:04 +02:00
Georgi Gerganov
2f9ec7e271
cuda : improve text-generation and batched decoding performance (#3776)
* cuda : prints wip

* cuda : new cublas gemm branch for multi-batch quantized src0

* cuda : add F32 sgemm branch

* cuda : fine-tune >= VOLTA params + use MMQ only for small batches

* cuda : remove duplicated cuBLAS GEMM code

* cuda : add CUDA_USE_TENSOR_CORES and GGML_CUDA_FORCE_MMQ macros

* build : add compile option to force use of MMQ kernels
2023-10-27 17:01:23 +03:00
Georgi Gerganov
6961c4bd0b
batched-bench : print params at start 2023-10-25 10:26:27 +03:00