Commit Graph

165 Commits

Author SHA1 Message Date
Georgi Gerganov
1d8fca72ae
metal : add GGML_OP_REPEAT kernels (#7557)
ggml-ci
2024-05-27 12:10:19 +03:00
Georgi Gerganov
62bfef5194
metal : disable FA kernel for HS=256 (#7556)
ggml-ci
2024-05-27 10:38:39 +03:00
Georgi Gerganov
e84b71c2c6
ggml : drop support for QK_K=64 (#7473)
* ggml : drop support for QK_K=64

ggml-ci

* opencl : restore QK_K=256 define
2024-05-23 10:00:21 +03:00
liuwei-git
201cc11afa
llama : add phi3 128K model support (#7225)
* add phi3 128k support in convert-hf-to-gguf

* add phi3 128k support in cuda

* address build warnings on llama.cpp

* adjust index value in cuda long rope freq factors

* add long rope support in ggml cpu backend

* make freq factors only depend on ctx size

* remove unused rope scaling type 'su' frin gguf converter

* fix flint warnings on convert-hf-to-gguf.py

* set to the short freq factor when context size is small than trained context size

* add one line of comments

* metal : support rope freq_factors

* ggml : update ggml_rope_ext API to support freq. factors

* backends : add dev messages to support rope freq. factors

* minor : style

* tests : update to use new rope API

* backends : fix pragma semicolons

* minor : cleanup

* llama : move rope factors from KV header to tensors

* llama : remove tmp assert

* cuda : fix compile warning

* convert : read/write n_head_kv

* llama : fix uninitialized tensors

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-05-21 23:28:32 +03:00
John Balis
48aa8fd1f2
ggml : add ggml_upscale_ext (ggml/814)
* initial commit with CPU implementation of upscale to shape and test, cuda implementation next

* experimental commit to see if dst shape is correct

* test version

* test

* removed unnecessary params

* refactor

* fixed tests

* ggml : metal impl + cleanup + sycl dev warnings

* patched ggml_upscale cuda op to handle non-contiguous tensors, added test for non-contiguous behavior

* metal : fix upsacle op to support nb00 + style

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-05-15 13:23:33 +03:00
Georgi Gerganov
e8a7fd4fb0
metal : support FA without mask + add asserts (#7278)
* ggml : fa without mask + add asserts

ggml-ci

* metal : support non-contiguous KV

ggml-ci
2024-05-14 19:09:30 +03:00
Georgi Gerganov
f308ea7059 metal : tune soft_max number of threads (whisper/0) 2024-05-14 19:08:09 +03:00
Georgi Gerganov
6aeff24f8b
metal : fix indent (ggml/0) 2024-05-11 21:34:21 +03:00
Justina Cho
f5ef34e428 feat: implemented sigmoid function (ggml/806)
* added sigmoid function

* implemented metal kernel for sigmoid

* implemented cuda kernel for sigmoid

* added sigmoid unary op and incremented count
2024-05-11 15:38:34 +03:00
Georgi Gerganov
9cb317f77e
ggml : full ALiBi support (#7192)
* ggml : full ALiBi support

* ggml : update ggml_soft_max_ext() CUDA, SYCL

* ggml : ggml_flash_attn_ext() support ALiBi (CPU)

* ggml : ggml_flash_attn_ext() support ALiBi (Metal)

* ggml : fix warning

* ggml : ggml_flash_attn_ext() support ALiBi (CUDA)

ggml-ci

* ggml : fix assert message

* vulkan : add dev notes

* ggml : require mask when using ALiBi

ggml-ci

* convert : fix convert for refact models
2024-05-11 10:32:41 +03:00
Georgi Gerganov
18e437665c
metal : fix flash attention kernel requirements (#7169)
* metal : fix flash attention kernel requirements

ggml-ci

* metal : fix ggml_metal_supports_op

ggml-ci
2024-05-10 18:20:10 +03:00
Gilad S
26458af1d6
metal : use vm_allocate instead of posix_memalign on macOS (#7078)
* fix: use `malloc` instead of `posix_memalign` in `ggml-metal.m` to make it not crash Electron proccesses

* fix: typo

* fix: use `vm_allocate` instead of `posix_memalign`

* fix: don't call `newBufferWithBytesNoCopy` with `NULL` when `ggml_metal_host_malloc` returns `NULL`

* fix: use `vm_allocate` only on macOS
2024-05-08 22:08:10 +03:00
Justine Tunney
3855416027
ggml : introduce bfloat16 support (#6412)
* Introduce bfloat16 support

Many models on Hugging Face (e.g. Mistral, TinyLLaMA) use bfloat16 as
their canonical floating point format.

      ┌sign
      │
      │   ┌exponent
      │   │
      │   │      ┌mantissa
      │   │      │
      │┌──┴───┐┌─┴───┐
    0b0000000000000000 brain16

This encoding has the same number of exponent bits as float32. That
makes conversion relatively straightforward, even in the absence of
hardware support. For example, converting brain16 to binary32 means
simply shifting 16 bits to the left.

      ┌sign
      │
      │   ┌exponent
      │   │
      │   │      ┌mantissa
      │   │      │
      │┌──┴───┐┌─┴───────────────────┐
    0b00000000000000000000000000000000 IEEE binary32

The issue is that converting bf16 to fp16 can result in information
loss. Only 13% of bf16 numbers can be precisely represented in fp16
which in practice ends up being 99.71% of Mistral 7b v0.2's weights
however there is currently no way other than fp32 to get the others

      ┌sign
      │
      │  ┌exponent
      │  │
      │  │    ┌mantissa
      │  │    │
      │┌─┴─┐┌─┴──────┐
    0b0000000000000000 IEEE binary16

This change fixes that, by adding a bf16 data type to GGML. Support
for CPU inference has been implemented along with optimizations for
the AVX2, AVX512, and AVX512BF16 ISAs. Perplexity on Mistral 7b 0.2
improves somewhere around -0.0024 to -0.0046 compared to using fp16

* Remove GGML code that's not needed

* Minimize the GGML API surface area for BF16

* Remove bf16 luts

* Make the GGML header look nicer

* Fix documentation

* Apply ggerganov's fixes for test-backend-ops

* Add BF16 code for new ggml_validate_row_data() function
2024-05-08 09:30:09 +03:00
Kevin Gibbons
f364eb6fb5
switch to using localizedDescription (#7010) 2024-04-30 17:14:02 +02:00
Georgi Gerganov
77e15bec62
metal : remove deprecated error code (#7008) 2024-04-30 15:52:21 +03:00
Kevin Gibbons
a68a1e7ed0
metal : log more info on error (#6987) 2024-04-30 12:34:50 +03:00
Georgi Gerganov
9c67c2773d
ggml : add Flash Attention (#5021)
* ggml : add ggml_flash_attn_ext API

* ggml : fix GQA support in ggml_flash_attn_ext

* ggml : online attention (CPU)

* metal : initial implementation

* metal : f16 precision

* metal : reduce branches

* metal : specialize for head size

* wip : 8 rows per simd group

* wip : 4 rows per simd group

* wip : template for rows per warp

* metal : parallelize across KV size

* metal : parallel reduce across heads

* metal : efficient flash_attn_f16 implementation

* metal : avoid redundant loads of the attention

* metal : scale and mask in matrix form

* metal : fix comment

* llama : avoid ggml_cast, use F32 query

* metal : add parallel reduce version (disabled)

* metal : move output into local memory + optimize

- the result from each simdgroup now stays in the registers
- significantly reduced SRAM usage
- more efficient skipping of -INF blocks
- avoid simdgroup barrier in hot loop
- add comments

* metal : add tests, fix scaling, support C > 32

* metal : improve precision

* ggml : fix f16 mad

* metal : minor

* metal : support Q > 8

* tests : add ATTN tests

* metal : disable buffer allocation logs

* tests : more

* metal : faster inner loop for C == 32

* metal : fix array initialization

* tests : ifdef

* ggml : switch to padded F16 mask for ggml_soft_max, ggml_flash_attn_ext

* ggml : fix ggml_soft_max mask requirement

* cuda : fix soft_max to use correct mask size

* cuda : add flash_attn kernel (wip)

* metal : optimize softmax for C > 32

* metal : optimize softmax

* tests : minor fix

* cuda : avoid zeroing fragments

* tests : update dims

* cuda : fix __hisinf() result check

* cuda : avoid warp_reduce for smax

* cuda : use int instead of int64_t

Noticeably improves performance (thanks to Johannes)

* cuda : make loops use the same loop values

Thanks Johannes again for the tip

* cuda : unroll some of the loops

* cuda : avoid __hisinf branches

* cuda : use half2 in softmax

* cuda : switch to 1 warp for bs > 16

* cuda : speed-up reduce part of the kernel

* cuda : unroll Q*K^T loop

* cuda : fix -INF block check

* cuda : simplify softmax

* cuda : fix matrix names

* cuda : minor

* llama : adapt to F16 KQ_pos

* llama : adapt new models to F16 KQ_mask

* ggml : fix F16 store (ARM NEON)

* llama : fix type of KQ_mask and KQ_pos

* ggml : fix CPU soft_max

* tests : add hs=256

* cuda : fix build

* metal : improve perf via smaller int registers

* cuda : adapt soft_max to F16 mask and pos

* CUDA: faster FlashAttention, kernel for bs == 1

* 16 cols for Phi-2

* no vec for hs, no hs==256 ncols==32 for Volta

* adjust kernel selection logic

* 4 warps, 256 stride for all D

* no ncols == 64

* Multiple parallel blocks for batch size 1

* fix compile warnings

* fix excessive KQ_b loads

* fix cmake build

* fix KV cache padding, NaN from INFINITY (#6438)

* llama : flash_attn cparam + fix defrag

* server: support flash_attn param

* server: bench: enable flash_attn param

* CUDA: refactor host code, dyn. par. blocks

* fix flash_attn_vec_f16 race condition

* flush softmax exp below threshold to 0

* store temp KQ in registers

* Calculate KQ as FP32 if KQV has GGML_PREC_F32

* Add __hgt2_mask implementation for CUDA 11

* fix KQ FP32 precision fpr parallel_blocks > 1

* llama-bench : add -fa,--flash-attn arg

* metal : add BS=1 kernel for flash attention (#6508)

* metal : add BS=1 kernel for flash attention (wip)

* metal : support more than 1 warps

* metal : opts

* metal : opt

* metal : switch to parallel reduce

* metal : reduce registers

* metal : simplify

* metal : initial FA vec kernel

* metal : use F32 attention accumulators

* batched-bench : add fattn arg

* llama : simplify llama_build_kv_store

ggml-ci

* llama : adapt build_olmo to changes

* ggml : fix arm fp16 store on windows

* metal : clean-up

* metal : clean-up kernel code

* metal : minor

* tests : remove benchmarks

ggml-ci

* ggml : fix avx512 const correctness

ggml-ci

* ggml : fix soft_max with bias on CPU

ggml-ci

* common : print --flash-attn in help

* ggml : fix num dimensions in ggml_flash_attn_ext

* llama : force disable flash attention for incompatible models

* ggml : ggml_soft_max support F16/F32 mask/pos

ggml-ci

* cuda : uint -> uint32_t

* cuda : "constexpr dim3" -> "const dim3"

ggml-ci

* cuda : try to fix __hgt2_mask

ggml-ci

* ggml : add TODO's for F16/F32 mask/pos support in other backends

* llama : replace bool need_kq_pos with use_alibi

* llama : prep ALiBi support for BERT models

ggml-ci

* llama : fix n_batch requirements

ggml-ci

* cont

* server : add help for --flash-attn arg

* llama : disable FA for AMD

* tests : remove TMP_ATTN_BENCH

ggml-ci

* llama : support save/load state with FA enabled

ggml-ci

* ci : add CUDA save-load-state tests

ggml-ci

* llama : llama_kv_cache_clear zeroes data + fix save-load seq

ggml-ci

* llama : fix copy-paste errors, add TODO

* llama : disallow incompatible states

* llama : update llama_state_get_size after v_trans field

* metal : remove tmp log

* llama : add static reminder for llama_state_get_size

* metal : fix max nsg

ggml-ci

* ci : fix arg order

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Pierrick HYMBERT <pierrick.hymbert@gmail.com>
2024-04-30 12:16:08 +03:00
slaren
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
* ggml : group all experts in a single ggml_mul_mat_id
cuda : improve mmid row copy

* cuda : fix bin bcast with non-cont src0

* test-backend-ops : only run all mul mat tests for base types

* llama : disable moe offloading with SYCL

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-18 15:18:48 +02:00
Shijie
f4dea7da18
llama : add qwen2moe (#6074)
* support qwen2moe

* fix-review

* metal : support unary ops for nelements % 4 != 0

* metal : require contiguousness for float4 unary kernels

* metal : require contiguousness for float4 unary kernels (cont)

* fix-review

* names : for brevity "SHARED_EXP" -> "SHEXP"

* llama : reuse build_moe_ffn()

* llama : add model type name

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-16 18:40:48 +03:00
Dave
422c2aff1c
Added support for GGML_OP_CLAMP in Metal (#6662)
* Added support for GGML_OP_CLAMP in Metal

* Corrected size

---------

Co-authored-by: dave-fl <dave@Davids-MacBook-Pro.local>
2024-04-14 13:14:19 +02:00
slaren
fbbc030ba9
metal : unify mul_mv_id kernels (#6556) 2024-04-12 18:13:20 +02:00
slaren
08a0c02060
ggml : mul_mat_id use the same tensor for all the experts (#6387)
* ggml : update mul_mat_id to use the same tensor for all the experts

* update cuda

* minor

* update metal

* update test-backend-ops

* fix cuda

* Update ggml-metal.m

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

* update convert.py

* update convert-hf-to-gguf.py

* update convert.py for mixtral hf models

* Update convert-hf-to-gguf.py

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

* cuda : support non-pow-2 number of experts

* allow quantize to work for split and merged experts models in the same way

* cleanup + disable mmap automatically with split tensors models

* update imatrix

* test-backend-ops : test qwen argsort

* update grok model loading

* llama : add merged experts tensors to the grok tensor map

* minor

* gguf : bump version

* fix quantizing of merged experts

* convert-hf-to-gguf.py : update grok (untested)

* make linter happy

* cuda/argsort : use shared memory instead of pool memory

* convert : fix grok tensor names

* metal : add support for non-pow-2 argsort

* llama : more loader cleanup, better error checking

* cuda : fix warning

* llama : still use mmap for loading old models, but copy the data to a host buffer

* add review note

* llama : remove ffn tensor counting + add sanity check

ggml-ci

* convert : fix handling of n_experts == None

ggml-ci

* imatrix : fix ncall counters

* llama : produce error if imatrix size does not match

* quantize : terminate on errors + trace logs

ggml-ci

* metal : pad shared memory to 16 bytes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-03 16:07:05 +03:00
compilade
557410b8f0
llama : greatly reduce output buffer memory usage (#6122)
* llama : greatly reduce logits memory usage

* llama : more compact state saving and reloading

* llama : fix lctx.n_outputs not being set before building graph

* perplexity : adapt to the logits API changes

* perplexity : fix Winogrande, use correct logits for second choice start

The first logits used to evaluate the second choice were not from
the end of the common prefix; instead, they were the logits from the end
of the first choice. This has been corrected.

The previous implementation sometimes had outliers in the scores of
choices for some tasks, and the logic to skip choices words
in the log-likelihood evaluation probably was an attempt to reduce those,
but it was complex and didn't quite seem to be the right thing.

This is simpler now, and the outlier scores aren't there anymore.

* perplexity : normalize spaces and punctuation in Winogrande sentences

* llama : fix embedding conditions

* llama : fix llama_get_embeddings_ith when the resulting id is 0

* llama : fix wrong n_outputs in llama_set_inputs

A mismatch happened when using a smaller n_ubatch than n_batch and then using
llama_batch_get_one(). The decision of what n_outputs should be now almost
fully depends on how lctx.n_outputs is set in llama_decode_internal.
The conditions are simpler this way.

* llama : when saving the state, recalculate n_outputs

This ensures the correct number of outputs for the entire previous batch
is stored in the session file, even when n_ubatch is smaller than n_batch.

* llama : fix not-skipping outputs of non-causal models

* llama : fix running a batch with n_outputs == 0

It previously worked because lctx.inp_out_ids was not initialized,
so it pointed to some garbage address which was somehow still valid when I
ran my tests.

* llama : keep same graph topology even when n_outputs == 0

* ggml : saner ggml_can_repeat with empty tensors

*  ggml : future-proof ggml_is_empty by using GGML_MAX_DIMS - 1

* ggml : do not multi-thread ops returning empty tensors

* ggml : make ggml_is_empty public and work with views

* llama : use a vector for ctx->output_ids

* llama : rework reallocation logic for llama_output_reserve

Now comparing the actual size with the new total size of the output buffer
to allow more efficient enabling and disabling of the embeddings
and/or logits output in the future.

* ggml : skip empty tensors in all backends

* llama : fix llama_output_reserve nullptr deref when new_size is 0

* perplexity : make Winogrande work as it does on master

The problems with the Winogrande implementation will
need to be fixed in a separate PR to ease review.

* llama : clearer error messages for invalid logits or embeddings ids

* llama : assert all models that can have inp_out_ids

Since the graph topology is now constant, this presence check
can be done even when there are no outputs.

* llama : assert logits and embd buffers exist before writing to them

* llama : handle errors from llama_output_reserve at call sites

* perplexity : make hellaswag and multiple-choice outputs identical to master

Due to how the KV cache is updated, the logprobs for tokens in a batch
are very slightly affected by the other tokens present in the batch,
so to make hellaswag and multiple-choice return exactly the same results
as on master, the last token of each sequence needs to be evaluated
even though its output is not used at all.

This will probably be changed back in the future to make these benchmarks
a tiny bit faster.

* perplexity : fix division by zero when using less than 100 multiple-choice tasks

* llama : allow loading state saved with a different ctx size

When loading a session file, the context size is now only required to be
at least enough to load the KV cells contained in that session file,
instead of requiring to use exactly the same context size as when saving.

Doing this enables the use-case of extending or shrinking the context size
of a saved session.

This breaks existing session files because the meaning of kv_buf_size
is slightly changed (previously it was the size of the whole KV cache,
now it's only the size of the saved part of it). This allows for
finer-grained sanity checks when loading in an effort to keep kv_buf_size
useful even when the kv_size is changed.

* llama : minor

ggml-ci

* readme : update recent API changes, and warn about Vulkan

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-26 16:46:41 +02:00
Kawrakow
55c1b2a3bb
IQ1_M: 1.75 bpw quantization (#6302)
* iq1_m: basics

* iq1_m: basics-2

* iq1_m: CUDA dequantize works

Very 1st shot I get PPL = 9.76 for LLaMA-v2-7B.

* iq1_m: separate shifts for each group of 8 in a block

We get
PPL(LLaMA-v2-7B ) = 9.2810
PPL(LLaMA-v2-13B) = 6.8105

Not bad, but slightly higher than
  sqrt(PPL(IQ1_S) * PPL(IQ2_XXS))
which is the expected outcome given that IQ1_M is
halfway between IQ1_S and IQ2_XXS in terms of bpw.
From this, we would expect
 PPL = 9.14 for LLaMA-v2-7B
 PPL = 6.63 for LLaMA-v2-13B

* iq1_m: go to 3-bit scales

There is slight increase in PPL, but the 0.0625 bpw reduction
in size is totally worth it.

We now have
PPL(LLaMA-v2-7B ) = 9.4469 at 1.96 bpw
PPL(LLaMA-v2-13B) = 6.8717 at 1.93 bpw
PPL(LLaMA-v2-70B) = 4.8568 at 1.85 bpw

* iq1_m: scalar dot product

* iq1_m: AVX2 dot product

* iq1_m: very slightly faster AVX2 dot product

* iq1_m: ARM_NEON dot product

Works, but very slow (10.5 t/s)

* iq1_m: Metal - dequantize works, dot product does not

* iq1_m: Metal now works

About the same performance as iq1_s.

* iq1_m: minor

* iq1_m: checking pure iq1_m quantization

It is pretty bad: PPL(LLaMA-v2-7B) = 34 if we quantize output.weight
with Q4_K.

* iiq1_m: slightly faster ARM_NEON dot product

10.5 t/s -> 11.65 t/s

* iq1_m: faster ARM_NEON dot product

11.65 t/s -> 14.9 t/s

* iq1_m: another minor ARM_NEON dot product improvement

14.9 -> 15.0 t/s

* iq1_m: small PPL improvement via super-block scale adjustment

After quantizing block scales redo the super-block scale fit.

PPL(LLaMA-v2-7B ) = 9.3346
PPL(LLaMA-v2-13B) = 6.8419
PPL(LLaMA-v2-70B) = 4.8294
PPL(Mistral-7B  ) = 8.1624

* iq1_m: adapt to CUDA refactoring

* iq1_m: remove unused variable

We have progressed to warnings being errors.

* iq1_m: add to backend-ops tests

* iq1_m: fix Windows ARM

* iq1_m: use common definition of iq1m_scale_t

* cuda: assert -> NO_DEVICE_CODE

* iq1_M: PR comments

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-26 15:21:27 +01:00
Georgi Gerganov
b3e94f26ba
metal : proper assert for mat-mat memory alignment (#6225)
* metal : proper assert for mat-mat memory alignment

ggml-ci

* readme : add notice about the bug fix

* metal : fix the fix

ggml-ci
2024-03-22 11:35:53 +02:00
Kawrakow
76aa30a263
Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized K cache (#6183)
* k_cache: be able to use Q5_0

* k_cache: be able to use Q5_1 on CODA

* k_cache: be able to use Q5_0 on Metal

* k_cache: be able to use Q5_1 on Metal

* k_cache: be able to use IQ4_NL - just CUDA for now

* k_cache: be able to use IQ4_NL on Metal

* k_cache: add newly added supported types to llama-bench and CUDA supports_op

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-21 08:27:57 +01:00
slaren
2bf8d0f7c4
backend : offload large batches to GPU (#6083)
* backend : offload large batches to GPU

* fix hip

* code cleanup

* fix CUDA split buffers

* Update ggml-backend-impl.h

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

* cuda : fix memset without set_device

* imatrix : remove sched affix from weight names

* sched : add a new split if the current one has too many inputs
reduce max inputs per split
more cleanup

* update backends

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2024-03-18 11:03:04 +01:00
Georgi Gerganov
381da2d9f0
metal : build metallib + fix embed path (#6015)
* metal : build metallib + fix embed path

ggml-ci

* metal : fix embed build + update library load logic

ggml-ci

* metal : fix embeded library build

ggml-ci

* ci : fix iOS builds to use embedded library
2024-03-14 11:55:23 +02:00
slaren
f30ea47a87
llama : add pipeline parallelism support (#6017)
* llama : add pipeline parallelism support for batch processing with multiple CUDA GPUs

ggml-ci

* server : add -ub, --ubatch-size parameter

* fix server embedding test

* llama : fix Mamba inference for pipeline parallelism

Tested to work correctly with both `main` and `parallel` examples.

* llama : limit max batch size to n_batch

* add LLAMA_SCHED_MAX_COPIES to configure the number of input copies for pipeline parallelism
default increase to 4 (from 2)

changing this value may improve performance for some systems, but increases memory usage

* fix hip build

* fix sycl build (disable cpy_tensor_async)

* fix hip build

* llama : limit n_batch and n_ubatch to n_ctx during context creation

* llama : fix norm backend

* batched-bench : sync after decode

* swiftui : sync after decode

* ggml : allow ggml_get_rows to use multiple threads if they are available

* check n_ubatch >= n_tokens with non-casual attention

* llama : do not limit n_batch to n_ctx with non-casual attn

* server : construct batch with size of llama_n_batch

* ggml_backend_cpu_graph_compute : fix return value when alloc fails

* llama : better n_batch and n_ubatch comment

* fix merge

* small fix

* reduce default n_batch to 2048

---------

Co-authored-by: Francis Couture-Harpin <git@compilade.net>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-13 18:54:21 +01:00
Georgi Gerganov
8030da7afe
ggml : reuse quantum structs across backends (#5943)
* ggml : reuse quant blocks across backends

ggml-ci

* ggml : define helper constants only for CUDA and SYCL

ggml-ci

* ggml : define helper quantum constants for SYCL

ggml-ci
2024-03-12 14:27:20 +02:00
Georgi Gerganov
bb6d00bbf9
metal : move mm_id indices to shared mem (#5982) 2024-03-10 23:12:48 +02:00
Michael Podvitskiy
9fa2627347 ggml : introduce ggml_status (ggml/750)
* using enum as an exit code instead of macros

* update return type from enum to unsigned int

* indentation fix

* compound update
ggml_compute_exit_code -> ggml_status
changed ggml_status from a bit-field type to simple codes
ggml_status to string cast

* ggml_status to string cast

* GGML_CALL was removed

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

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-04 20:54:23 +02:00
leejet
7d43c585dc
add some new ops, fix some operators and add batch operations to certain operators. (ggml/747)
* cuda: fix group_norm

* cuda: add batch inference support for ggml_pad/ggml_upscale

* add ggml_arrange

* add ggml_timestep_embedding

* update ggml_arange/ggml_timestep_embedding tests

* cuda: fix im2col

* add ggml_arange/ggml_timestep_embbeding support for metal backend

* fix some bugs

* fix some bugs

* Update ggml.h

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

* Update ggml-cuda.cu

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

* Update ggml-metal.m

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

* Update ggml-metal.m

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

* Update ggml-metal.metal

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

* modify according to the review comments

* ggml : fix compile warnings + code style

* ggml : normalize compute_forward calls + fix seg fault in debug

* minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
2024-03-04 10:39:10 +02:00
UEXTM.com
5f70671856
Introduce backend GUIDs (ggml/743)
* Introduce backend GUIDs

Initial proposed implementation of backend GUIDs
(Discussed in https://github.com/ggerganov/ggml/pull/741)

Hardcoded CPU backend GUID (for now)
Change ggml_backend_is_cpu logic to use GUID

* Remove redundant functions

Remove redundant functions `ggml_backend_i::get_name` and `ggml_backend_guid` which are not desired for future expansion

* Add spaces to match style

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

* Fix brace style to match

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

* Add void to () in function signature

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

* Add back ggml_backend_guid and make CPU_GUID a local static in ggml_backend_cpu_guid

* add guids to all backends

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-02-28 11:17:05 +02:00
Kawrakow
0becb22ac0
IQ4_XS: a 4.25 bpw quantization (#5747)
* Try IQ4_NL with blocks of 64 - does not look good

* iq4_xs: go to super-blocks of 256 and 6-bit scales for blocks of 32

* iq4_xs: CUDA works - 133.2 t/s

* iq4_xs: AVX2 dot product

* iq4_xs: ARM_NEON dot product

* iq4_nl: Metal implementation

As usual, Metal / Apple Silicon don't like my quants.

* iq3_xs: minor fix

* iq4_xs: shrink by using IQ3_S for attn_k and attn_q

* iq4_xs: revert using IQ3_S for attn_k and attn_v

PPL vs size is good, but CPU performance suffers: on M2 Max
TG-128 drops to 21.7 t/s from 28.8, and on a Ryzen-7950X
to 14.5 t/s from 15.8 t/s. On CUDA we have 135 t/s when
using IQ3_S vs 133 t/s with pure IQ4_XS.

* Fix CI

* iq4_xs: Added forgotten check for 256 divisibility

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-27 16:34:24 +02:00
Kawrakow
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)
* Adding IQ2_S and IQ2_M as a single cumulative commit

* Update examples/quantize/quantize.cpp

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

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-02-26 18:28:38 +02:00
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