* 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>
* 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
* cmake : add helper for faster CUDA builds
* batched : add NGL arg
* ggml : skip nops in compute_forward
* cuda : minor indentation
* cuda : batched cuBLAS GEMMs for src0 F16 and src1 F32 (attention ops)
* Apply suggestions from code review
These changes plus:
```c++
#define cublasGemmBatchedEx hipblasGemmBatchedEx
```
are needed to compile with ROCM. I haven't done performance testing, but it seems to work.
I couldn't figure out how to propose a change for lines outside what the pull changed, also this is the first time trying to create a multi-part review so please forgive me if I mess something up.
* cuda : add ROCm / hipBLAS cublasGemmBatchedEx define
* cuda : add cublasGemmStridedBatchedEx for non-broadcasted cases
* cuda : reduce mallocs in cublasGemmBatchedEx branch
* cuda : add TODO for calling cublas from kernel + using mem pool
---------
Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
* CUDA: added support for ggml_clamp (see also: https://github.com/ggerganov/ggml/issues/545)
* mpt : added an implementation based (mostly) on falcon integration, modified with deltas from ggml/examples/mpt
* mpt : protect against "clip_qkv": null in mpt-7b
* mpt : quick fix to avoid "Strange model" warning when quantizing MPT models
* mpt : addendum to changeset:84e30e8 - leave parameter clamp_kqv out from metadata rather than use 0.0 to indicate "no clamping" (more compliant with the current GGUF spec?)
* mpt : standardized all tensor names to follow GGUF spec
* mpt : addendum to changeset:1be89c40 - use "req" parameter of GGUF_GET_KEY macro instead of duplicate code
* mpt : fixed comment s/gptneox/mpt/
* mpt : remove tabs, trailing whitespace
* mpt : removed ne01 + n_past == ne00 assertion from alibi (cuda/f32) and rope_shift from build_mpt
* mpt : updated convert-mpt-hf-to-gguf.py to reflect changes made to convert-gptneox-hf-to-gguf.py in pr:3252
* comment out n_past instead of marking it unused
* mpt : removed hardcoded +178 from convert script in favor of utilizing hparams["vocab_size"]
* mpt : remove unused tokenizer_json in convert script
* ggml : remove obsolete n_past assert in ggml_alibi
* llama : print clam_kqv and max_alibi_bias hparams
---------
Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* ggml-cuda : perform cublas matrix multiplication of quantized types as fp16
* rename CC_TURING to CC_VOLTA
* disable fp16 mat mul completely with multi GPU
* llama.cpp : split llama_context_params into model and context params
ggml-ci
* fix metal build
* fix freq_base/scale default to model value
* llama-bench : keep the same model between tests when possible
* move n_threads to llama_context_params, add n_threads_batch
* fix mpi build
* remove kv_size(), cuda scratch fixes
* remove low-vram option
* add n_threads_batch to system info, refactor to get_system_info()
* add documentation about --threads-batch to the READMEs
* llama-bench fix
* main : fix rope freq/scale warning
* llama.cpp : add llama_get_model
common : add llama_tokenize from model
* remove duplicated ctx/model functions
ggml-ci
* cuda : print total VRAM used
* Make ggml-cuda.cu build with QK_K = 64
Using LLAMA_CUDA_FORCE_DMMV = ON and -nommq it runs and produces
a meaningful result.
* k_quants tuning for Falcon-7b
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* use hipblas based on cublas
* Update Makefile for the Cuda kernels
* Expand arch list and make it overrideable
* Fix multi GPU on multiple amd architectures with rocblas_initialize() (#5)
* add hipBLAS to README
* new build arg LLAMA_CUDA_MMQ_Y
* fix half2 decomposition
* Add intrinsics polyfills for AMD
* AMD assembly optimized __dp4a
* Allow overriding CC_TURING
* use "ROCm" instead of "CUDA"
* ignore all build dirs
* Add Dockerfiles
* fix llama-bench
* fix -nommq help for non CUDA/HIP
---------
Co-authored-by: YellowRoseCx <80486540+YellowRoseCx@users.noreply.github.com>
Co-authored-by: ardfork <134447697+ardfork@users.noreply.github.com>
Co-authored-by: funnbot <22226942+funnbot@users.noreply.github.com>
Co-authored-by: Engininja2 <139037756+Engininja2@users.noreply.github.com>
Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
Co-authored-by: jammm <2500920+jammm@users.noreply.github.com>
Co-authored-by: jdecourval <7315817+jdecourval@users.noreply.github.com>
use a different function for no_alloc to avoid breaking backwards compat, fixes lora
remove 512 n_batch limit
fixed 2048 batch size
cleanup
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* llama : add benchmark example
* add to examples CMakeLists.txt
* fix msvc build
* add missing include
* add Bessel's correction to stdev calculation
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* improve markdown formatting
* add missing include
* print warning is NDEBUG is not defined
* remove n_prompt and n_gen from the matrix, use each value separately instead
* better checks for non-optimized builds
* llama.cpp : fix MEM_REQ_SCRATCH0 reusing the value of n_ctx of the first call
* fix json formatting
* add sql output
* add basic cpu and gpu info (linx/cuda only)
* markdown: also show values that differ from the default
* markdown: add build id
* cleanup
* improve formatting
* formatting
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* make rms_norm_eps a parameter
* add rms_norm_eps to command line
* fix baby llama, test-grad0
* use scientific notation for eps param in the help
ggml-ci
* Custom RoPE + bettter memory management for CUDA
* Adjusted look ahead in ggml_cuda_pool_malloc to 5%
This is sufficient it seems.
We end up using about 200 MB less VRAM that way when running
the 13B model with context 8192.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* k_quants: WIP super-blocks with 64 weights
* k_quants: WIP super-blocks with 64 weights
Q6_K scalar and AVX2 works
* k_quants: WIP super-blocks with 64 weights
Q4_K scalar and AVX2 works
* k_quants: WIP super-blocks with 64 weights
Q2_K scalar and AVX2 works. Q2_K is way too slow (it is actually slower
than the scalar implementation)
* k_quants: WIP super-blocks with 64 weights
Q3_K scalar and AVX2 works.
* k_quants: WIP super-blocks with 64 weights
Q5_K scalar and AVX2 works, and with that all
k_quants are done on AVX2 and scalar
* k_quants: WIP super-blocks with 64 weights
Q6_K working on CUDA. Cannot make it run quite as gast as
with super-blocks with 256 weigths: 8% slower on 4080,
20% slower on the 1660 (but there we fit 1 less layer on the
GPU because pf the larger model size), so some fraction of
these 20% is due to that,
* k_quants: WIP super-blocks with 64 weights
Q4_K working on CUDA. ~10% slower on GTX-1660,
16% slower on 4080.
* k_quants: WIP super-blocks with 64 weights
Q2_K working on CUDA. ~3% slower on GTX-1660,
10% slower on 4080.
* k_quants: WIP super-blocks with 64 weights
Q3_K working on CUDA.
* k_quants: WIP super-blocks with 64 weights
Q5_K working on CUDA, and with this CUDA is done.
* k_quants: WIP super-blocks with 64 weights
Q6_K working on ARM_NEON
* k_quants: WIP super-blocks with 64 weights
Q4_K working on ARM_NEON, but quite a bit slower than 256 weights
* k_quants: WIP super-blocks with 64 weights
Q2_K working on ARM_NEON, but quite a bit slower than 256 weights
* k_quants: WIP super-blocks with 64 weights
Q3_K working on ARM_NEON, but quite a bit slower than 256 weights.
* k_quants: WIP super-blocks with 64 weights
Q5_K working on ARM_NEON, but quite a bit slower than 256 weights.
With that, we have full support for ARM_NEON, although
performance is not quite there.
* k_quants: WIP super-blocks with 64 weights
Slightly more efficient Q3_K and Q5_K
* k_quants: WIP super-blocks with 64 weights
Another small improvement for Q3_K and Q5_K on ARM_NEON
* k_quants: WIP super-blocks with 64 weights
Yet another speedup for Q5_K on ARM_NEON.
We are now within 10% of the QK_K = 256 version.
* k_quants: WIP super-blocks with 64 weights
* We are able to pass preprocessor macros to the Metal
compiler
* Q6_K works and is actually slightly more efficient than
the QK_K = 256 version (25.2 ms vs 25.8 ms)
* k_quants: WIP super-blocks with 64 weights
Q4_K works on Metal and is actually slightly faster
than QK_K = 256 (21.95 ms vs 24.0 ms).
* k_quants: WIP super-blocks with 64 weights
Q2_K works on Metal and is very slightly faster
than QK_K = 256 (23.8 ms vs 24.2 ms).
* k_quants: WIP super-blocks with 64 weights
Q3_K works on Metal and is slightly faster
than QK_K = 256 (26.6 ms vs 28.3 ms).
* k_quants: WIP super-blocks with 64 weights
Q5_K works on Metal and is slightly faster
than QK_K = 256 (23.7 ms vs 26.3 ms).
* k_quants: call them _K, not _k, also on Metal
* k_quants: correctly define QK_K in llama.cpp
* Fixed bug in q4_K quantization added with the 64-block addition
* Simplify via lambda
* k_quants: swicth Q3_K to 4-bit scales when QK_K = 64
Otherwise there isn't much benefit from this
quantization type. There is some very slight loss
in accuracy, but we reduce size by ~7%.
E.g., for OpenLLaMA-3B, Q3_K_S perplexity is
8.6131 with 8-bit scales and 8.6352 with 4-bit,
while file size decreases from 1.53G to 1.44G.
* k_quants: switch Q4_K to 4-bit scales when QK_K = 64
Here the loss in accuracy is greater than for Q3_K,
but the Q4_K points still move further to the left on
the perplexity vs size curve.
* k_quants: forgot to add the Metal changes in last commit
* k_quants: change Q5_K to be type 0 when QK_K = 64
Still needs AVX2 implementation
* k_quants: AVX2 implementation for new 64-weight Q5_K
* k_quants: 10% faster ARM_NEON Q5_K dot product
* k_quants: fixed issue caused by merging with master
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* #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>
* k_quants: hopefully much faster Q4_K on older GPUs
On the GTX-1660 that I have available to represent
"old GPUs", token prediction drops from 65.5 ms/tok
to 41.5 ms/tok!
* k_quants: hopefully much faster Q3_K on older GPUs
On the GTX-1660 that I have available to represent
"old GPUs", token prediction drops from 60.3 ms/tok
to 41.0 ms/tok!
* k_quants: faster Q2_K on older GPUs
It looks like I didn't need to change anything
compared to what we already had, so this is just
adding clarifying comments. But I now measure
36.3 ms/tok on the GTX-1660, instead fo the
47.2 ms/tok that I have written in the faster
k-quants PR.
* k_quants: faster Q5_K on older GPUs
68.5 ms/tok -> 62.0 ms/tok on GTX-1660.
For some reason the same access pattern that leads
to such resounding success for Q2_K to Q4_K did not
work at all for Q5_K.
It is also more difficult to measure because for Q5_K_S
we only have 32 layers on the GTX-1660, so output, tok embeddings
and kv cache are done on the CPU.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Convert vector to f16 for dmmv
* compile option
* Added compilation option description to README
* Changed cmake CUDA_ARCHITECTURES from "OFF" to "native"
* cuda : faster k-quant dot kernels
* Imrove Q2_K dot kernel on older GPUs
We now have a K_QUANTS_PER_ITERATION macro, which should be
set to 1 on older and to 2 on newer GPUs.
With this, we preserve the performance of the original
PR on RTX-4080, and are faster compared to master on
GTX-1660.
* Imrove Q6_K dot kernel on older GPUs
Using the same K_QUANTS_PER_ITERATION macro as last commit,
we preserve performance on RTX-4080 and speed up
Q6_K on a GTX-1660.
* Add LLAMA_CUDA_KQUANTS_ITER to CMakeLists.txt and Makefile
Allowed values are 1 or 2. 2 gives the best performance on
modern GPUs and is set as default. On older GPUs 1 may work
better.
* PR comments
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Rebase to latest
* Show progress
* Add assert to make sure we only allocate temp buffer for non-CPU backend tensor
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* 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>
* xor hack
* block y dim
* loop unrolling
* Fixed cmake LLAMA_CUDA_BY option
* Removed hipblas compatibility code
* Define GGML_CUDA_DMMV_BLOCK_Y if not defined
* Fewer iters, more ops per iter
* Renamed DMMV X/Y compilation options
* Broadcasting for ggml_mul
* CUDA kernel for ggml_mul, norms in VRAM
* GPU weights not in RAM, direct loading with cuFile
* fixup! GPU weights not in RAM, direct loading with cuFile
* fixup! GPU weights not in RAM, direct loading with cuFile
* define default model path once, sync path with readme (#1366)
* ~7% faster Q5_1 AVX2 code (#1477)
* convert.py: Support models which are stored in a single pytorch_model.bin (#1469)
* Support models in a single pytorch_model.bin
* Remove spurious line with typo
* benchmark-matmul: Print the average of the test results (#1490)
* Remove unused n_parts parameter (#1509)
* Fixes#1511 lambda issue for w64devkit (mingw) (#1513)
* Fix for w64devkit and mingw
* make kv_f16 the default for api users (#1517)
* minor : fix compile warnings
* readme : adds WizardLM to the list of supported models (#1485)
* main : make reverse prompt option act as a stop token in non-interactive mode (#1032)
* Make reverse prompt option act as a stop token in non-interactive scenarios
* Making requested review changes
* Update gpt_params_parse and fix a merge error
* Revert "Update gpt_params_parse and fix a merge error"
This reverts commit 2bb2ff1748.
* Update gpt_params_parse and fix a merge error take 2
* examples : add persistent chat (#1495)
* examples : add persistent chat
* examples : fix whitespace
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* tests : add missing header
* ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508)
* ggml : use F16 instead of F32 in Q4_0, Q4_1 and Q8_0
* llama : bump LLAMA_FILE_VERSION to 3
* cuda : update Q4 and Q8 dequantize kernels
* ggml : fix AVX dot products
* readme : update performance table + hot topics
* ggml : fix scalar implementation of Q4_1 dot
* llama : fix compile warnings in llama_set_state_data()
* llama : fix name shadowing and C4146 (#1526)
* Fix name shadowing and C4146
* Fix if macros not using defined when required
* Update llama-util.h
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Update llama-util.h
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Code style
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Fix for mingw (#1462)
* llama : add llama_init_backend() API (close#1527)
* feature : add blis and other BLAS implementation support (#1502)
* feature: add blis support
* feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927
* fix: version detection for BLA_SIZEOF_INTEGER, recover min version of cmake
* Fix typo in INTEGER
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Revert "feature : add blis and other BLAS implementation support (#1502)"
This reverts commit 07e9ace0f9.
* GPU weights not in RAM, direct loading with cuFile
* llama : code style fixes + progress print fix
* ggml : ggml_mul better broadcast support
* cmake : workarounds for cufile when CMake version < 3.25
* gg rebase fixup
* Loop in llama.cpp, fixed progress callback
* Attempt clang-tidy fix
* llama : fix vram size computation
* Add forgotten fclose()
---------
Co-authored-by: András Salamon <ott2@users.noreply.github.com>
Co-authored-by: Ilya Kurdyukov <59548320+ilyakurdyukov@users.noreply.github.com>
Co-authored-by: Tom Jobbins <784313+TheBloke@users.noreply.github.com>
Co-authored-by: rankaiyx <rankaiyx@rankaiyx.com>
Co-authored-by: Stephan Walter <stephan@walter.name>
Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com>
Co-authored-by: Erik Scholz <Green-Sky@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: David Kennedy <dakennedyd@gmail.com>
Co-authored-by: Jason McCartney <jmac@theroot.org>
Co-authored-by: Evan Jones <evan.q.jones@gmail.com>
Co-authored-by: Maxime <672982+maximegmd@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Zenix <zenixls2@gmail.com>
