Commit Graph

54 Commits

Author SHA1 Message Date
AidanBeltonS
5487593bc7
Add freq factors (#7495) 2024-05-27 18:04:09 +05:30
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
AidanBeltonS
6bf9b66fa3
[SYCL] Update SYCL upscale operation (#7321)
* Update SYCL upscale operation

* Formatting

* Remove messages
2024-05-20 16:38:23 +05:30
AidanBeltonS
9a17ab914b
Add missing " (#7303) 2024-05-15 17:56:30 +05:30
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
Neo Zhang
948f4ec7c5
[SYCL] rm wait() (#7233) 2024-05-13 18:11:26 +08:00
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
Ouadie EL FAROUKI
8c570c9496
Minor arithmetic improvement to mmvq wrapper kernel (#7172) 2024-05-10 08:32:15 +08:00
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
Neo Zhang
ce023f6f2f
add device version in device list (#6959)
Co-authored-by: arthw <>
2024-04-28 22:40:31 +08:00
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
Neo Zhang Jianyu
17e98d4c96
fix mul_mat_id() for new input, make the ut pass (#6682) 2024-04-15 17:12:26 +08:00
Neo Zhang Jianyu
de17e3f745
fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)
* disable mmap to fix memcpy crash, add missed cmd in guide, fix softmax

* refactor to disable mmap for SYCL backend

* fix compile error in other os

* refactor the solution, use host buf to fix it, instead of disable mmap

* keep to support mmap()

* use host buff to reduce malloc times

* revert to malloc/free solution, for threaad safe
2024-04-14 10:42:29 +08:00
Abhilash Majumder
87fb5b4234
remove row=1 cond (#6532) 2024-04-08 16:26:01 +08:00
Neo Zhang Jianyu
d4f220a5cc
support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M (#6521) 2024-04-07 10:55:59 +08:00
Ouadie EL FAROUKI
1b496a745c
[SYCL] Fixed minor bug when enabling FP16 for non intel targets (#6464)
* moved INTEL_MKL guard from gemm_impl to gemm (wrapper)

* Update ggml-sycl.cpp

Co-authored-by: AidanBeltonS <87009434+AidanBeltonS@users.noreply.github.com>

---------

Co-authored-by: AidanBeltonS <87009434+AidanBeltonS@users.noreply.github.com>
2024-04-05 19:05:06 +05:30
Meng, Hengyu
52604860f9
[SYCL] Disable iqx on windows as WA (#6435)
* disable iqx on windows as WA

* array instead of global_memory
2024-04-03 10:34:40 +08:00
Neo Zhang Jianyu
25f4a613c4
[SYCL] fix set main gpu crash (#6339) 2024-03-28 08:55:24 +08:00
AidanBeltonS
e82f9e2b83
[SYCL] Fix batched impl for NVidia GPU (#6164)
* Fix batched impl

* Maintain previous behaviour for igpu

* retrigger CI

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-03-27 13:46:40 +05:30
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
Meng, Hengyu
ddf6568510
[SYCL] offload op (#6217)
* remove no USM methods

* leave the schedule to ggml_backend_sched entirely
2024-03-24 12:04:25 +08:00
AidanBeltonS
c5b8595e3f
Add nvidia and amd backends (#6157) 2024-03-21 11:40:52 +05:30
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
Neo Zhang Jianyu
46acb36767
fix set main gpu error (#6073) 2024-03-15 18:53:53 +08:00
AidanBeltonS
753e36f650
[SYCL] Fix non-intel device selection (#6042)
* Fix non-intel device selection

* Update ggml-sycl.cpp

Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>

* Update ggml-sycl.cpp

Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>
2024-03-15 14:56:20 +05:30
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
AidanBeltonS
b3d978600f
Update get version (#6025) 2024-03-13 18:47:54 +05:30
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
48358b2e5b
sycl : update IQ1_S kernels (WIP - not working!) (#5995)
* sycl : try to fix after IQ1_S changes

* sycl : iq1s_grid -> iq1s_grid_gpu

* sycl : fix grid type
2024-03-12 11:15:05 +02:00
Abhilash Majumder
ef3ced26a3
[SYCL] Add q3_s and q1_s (#5886)
* Add q3_s and q1_s

* fix compilation

* fix build

* fix build

* fix build

* enable ops

* rm macro

* increase grid space
2024-03-11 10:27:56 +05:30
Georgi Gerganov
8a3012a4ad
ggml : add ggml-common.h to deduplicate shared code (#5940)
* ggml : add ggml-common.h to shared code

ggml-ci

* scripts : update sync scripts

* sycl : reuse quantum tables

ggml-ci

* ggml : minor

* ggml : minor

* sycl : try to fix build
2024-03-09 12:47:57 +02:00
Neo Zhang Jianyu
89fb735fcf
Revert "[SYCL] fix error when set main gpu to non-zero (#5901)" (#5918)
This reverts commit ceca1aef07.
2024-03-07 12:14:49 +01:00
Neo Zhang Jianyu
ceca1aef07
[SYCL] fix error when set main gpu to non-zero (#5901)
* fix error when set main gpu to non-zero

* fix delete condition
2024-03-07 16:34:31 +08:00
Neo Zhang Jianyu
8ced9f7e32
add wait() to make code stable (#5895) 2024-03-06 12:08:32 +08:00
Neo Zhang Jianyu
21b0867433
[SYCL] fix mul_mat fault in CI/unit-test (#5862)
* fix mul_mat fault in cpy_f32_f16

* rm unused function

* add wait() for memcpy

* restore ci/run.sh, rename struct defination, fix bug in ggml_sycl_op_mul_mat_sycl

* fix format issue

* llama : fix segfault from unknown model arch name (#5820)

* llama : fix segfault from unknown model arch name

* llama : make all LLM maps const

This also requires using `std::map::at` instead of its `operator[]`
which does not exist for const maps.

* llama : name LLM_ARCH_UNKNOWN to "(unknown)"

This avoids errors from `std::map::at` when
getting the general name of the model architecture.
Using "(unknown)" instead of an empty string as per suggestion
https://github.com/ggerganov/llama.cpp/pull/5820#issuecomment-1973735284

* llama : remove redundant inner const for LLM_TENSOR_NAMES

The extra const won't do anything here as const maps
return const references to values.

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

* llama : remove redundant nullptr check in llm_arch_from_string

Since LLM_ARCH_NAMES is a const map, no spurious elements
with a NULL name are inserted anymore, so this check is dead code.

---------

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

* llama : refactor internal quantization functions (#5830)

* scripts : add pod-llama.sh

* ggml : IQ3_S improvements (#5829)

* iq3_s: somewhat faster AVX2 dot product

On Ryzen a 7950X TG-128 increases to 16 t/s from 15.5 t/s using
16 threads. For 8 threads it is 13.85 t/s vs 11.75 t/s.
PP-512 increases to 28.5 t/s from 23.8 t/s.

* iq3_s: somewhat faster ARM_NEON dot product

Still dog slow - 10.7 t/s up from 9.9 t/s.

* iq3_s: another small ARM_NEON improvement

10.7 -> 11.0 t/s. Using vmulq_s8 is faster than the xor - sub trick
that works best on AVX2.

* iq3_s: minor improvement on Metal

49.4 t/s -> 50.3 t/s

* iq3_s: PPL improvement

E.g., for a context of 4096 LLaMA-v2-7B goes to 5.1340 from 5.1653.

* iq3_s: use new grid everywhere

* Fix ARM_NEON

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

* convert-hf : make model class definitions self-contained (#5825)

* convert : automatically fall back to HfVocab if tokenizer.model doesn't exist (#5821)

* ggml : fix IQ3_S AVX implementation (#5834)

ggml-ci

* llama : add abort_callback to interrupt computation (#5409)

* using abort_callback from ggml to stop llama computation

* format fix

* a brief explaining comment

---------

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

* server: tests: passkey challenge /  self-extend with context shift demo (#5832)

* server: tests: add models endpoint scenario

* server: /v1/models add some metadata

* server: tests: add debug field in context before scenario

* server: tests: download model from HF, add batch size

* server: tests: add passkey test

* server: tests: add group attention params

* server: do not truncate prompt tokens if self-extend through group attention is enabled

* server: logs: do not truncate log values

* server: tests - passkey - first good working value of nga

* server: tests: fix server timeout

* server: tests: fix passkey, add doc, fix regex content matching, fix timeout

* server: tests: fix regex content matching

* server: tests: schedule slow tests on master

* server: metrics: fix when no prompt processed

* server: tests: self-extend add llama-2-7B and Mixtral-8x7B-v0.1

* server: tests: increase timeout for completion

* server: tests: keep only the PHI-2 test

* server: tests: passkey add a negative test

* flake.lock: Update (#5842)

Flake lock file updates:

• Updated input 'flake-parts':
    'github:hercules-ci/flake-parts/b253292d9c0a5ead9bc98c4e9a26c6312e27d69f' (2024-02-01)
  → 'github:hercules-ci/flake-parts/f7b3c975cf067e56e7cda6cb098ebe3fb4d74ca2' (2024-03-01)
• Updated input 'flake-parts/nixpkgs-lib':
    'github:NixOS/nixpkgs/97b17f32362e475016f942bbdfda4a4a72a8a652?dir=lib' (2024-01-29)
  → 'github:NixOS/nixpkgs/1536926ef5621b09bba54035ae2bb6d806d72ac8?dir=lib' (2024-02-29)
• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/cbc4211f0afffe6dfd2478a62615dd5175a13f9a' (2024-02-23)
  → 'github:NixOS/nixpkgs/1536926ef5621b09bba54035ae2bb6d806d72ac8' (2024-02-29)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* server : init http requests thread pool with --parallel if set (#5836)

* ci : schedule slow server tests only on Release or on demand (#5839)

* llama : fix llama_copy_state_data with fragmented KV cache (#5840)

The row size of the saved states was based on kv_self.head while
it should be based on llama_kv_cache_cell_max.

Existing session files should still work.

* llama : fix llama_kv_cache_cell_max inability to return 1

I've also changed its return type to uint32_t,
because this function is always used to set the value of uint32_t variables,
and because the index already has this type.

* llama : fix state size calculation

Some bytes in the state were unaccounted for in llama_get_state_size.
Since the logits reserve so much space, it did not cause problems.

* gguf-dump : support i-quants (#5841)

Co-authored-by: Black_Fox <radekliska@gmail.com>

* llama : allow for user specified embedding pooling type (#5849)

* allow for user specified pooling type

* llama : use enum types over int

---------

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

* readme : add API changes section

* cuda : fix data race in soft max (#5853)

* main : support special tokens as reverse/anti prompt (#5847)

* Support special tokens as reverse/anti prompt.

* Tokenize antiprompts only once.

* main : minor

---------

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

* common : use LLAMA_DEFAULT_SEED (#5855)

* 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>

* sync : ggml

* add alias for chat template (#5858)

* speculative : implement stochastic speculative sampling (#5625)

* (WIP) Implement stochastic speculative decoding

* sample from residual distribution on draft accept failure

* fix #5657: force greedy sampling with probs when temp is 0

* remove p_accept parameter

* fix style

* remove unused variables

* add srand() in speculative.cpp

* replace use of rand() with mt19937 sampling

* fixes based on review (@JohannesGaessler)

* fix r random generation

* randomly select next sequence to verify + fix bug in memory freeing

* fix bug in active_seqs sync

* fix uniform int distribution initialization

* remove warnings from comparison between int and size_t

* check grammar in `llama_sample_probability_distribution_impl`

* remove malloc code by utilizing vectors

* add PR link to README

* cmake : handle cases where git index is not found in .git (#5844)

* Update CMakeLists.txt

* Update CMakeLists.txt

* 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>

* sync : ggml

ggml-ci

* ggml : fix unknown status (#0)

* flake : fix

* llama : fix embeddings (#5796)

* llama : fix embeddings

ggml-ci

* llama : do not use KV cache for non-causal models

ggml-ci

* embeddings : fix llama_batch_init arg

* llama : add pooling switch

* llama : distinguish token vs sequence embeddings

ggml-ci

* llama : assert pooling tensor

* llama : simplify causal mask condition

ggml-ci

* llama : assert input batch with pooling enabled

* readme : update API changes list

* nix: static build (#5814)

* fix speculative decoding build on windows (#5874)

* rebase and rm tailing space

---------

Co-authored-by: LiangtaoJin <liang-tao.jin@intel.com>
Co-authored-by: compilade <113953597+compilade@users.noreply.github.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Kawrakow <48489457+ikawrakow@users.noreply.github.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Michael Podvitskiy <podvitskiymichael@gmail.com>
Co-authored-by: Pierrick Hymbert <pierrick.hymbert@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Nindaleth <Nindaleth@users.noreply.github.com>
Co-authored-by: Black_Fox <radekliska@gmail.com>
Co-authored-by: Douglas Hanley <thesecretaryofwar@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: DAN™ <dranger003@gmail.com>
Co-authored-by: leejet <leejet714@gmail.com>
Co-authored-by: Minsoo Cheong <54794500+mscheong01@users.noreply.github.com>
Co-authored-by: Dane Madsen <dane_madsen@hotmail.com>
Co-authored-by: hutli <6594598+hutli@users.noreply.github.com>
Co-authored-by: Jeffrey Quesnelle <emozilla@nousresearch.com>
2024-03-05 13:38:35 +05:30
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
Neo Zhang Jianyu
715641391d
Support multiple GPUs (split mode) on SYCL backend (#5806)
* suport multiple cards: split-mode - layer|row

* rm warning

* rebase with master, support tow new OPs, close feature for -sm=row, fix for unit test

* update news

* fix merge error

* update according to review comments
2024-03-02 19:49:30 +08:00
AidanBeltonS
38d1521608
[SYCL] Use batched mul_mat pathway (#5591)
* Use batched mul_mat pathway

* rm extra line

* Explicitly state scaled data type

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-03-01 13:06:47 +05:30
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
AidanBeltonS
e849078c6e
[SYCL] Add support for soft_max ALiBi (#5639)
* Add support for bias

* Update pre-processor

* rm commented code

* fix format

* fix CI

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-02-26 19:32:11 +05:30
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
Meng, Hengyu
88c46cbdac
[SYCL] conext add name (#5624)
* [SYCL] conext add name

* name should start with SYCL*
2024-02-21 17:52:06 +08:00
AidanBeltonS
b9111bd209
Update ggml_sycl_op_mul_mat_vec_q (#5502)
* Update ggml_sycl_op_mul_mat_vec_q

* Apply suggestions from code review

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

* revert suggestion on macro

* fix bug

* Add quant type GGML_TYPE_IQ1_S to unsupported

* fix format

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-02-20 12:31:25 +05:30
Abhilash Majumder
43fe07c1a4
ggml-sycl: Replace 3d ops with macro (#5458)
* use macro

* use macro

* fix format
2024-02-12 20:22:05 +05:30
Abhilash Majumder
6e99f2a04f
Fix f16_sycl cpy call from Arc (#5411)
* fix f16_sycl cpy call

* rm old logic

* add fp16 build CI

* use macro

* format fix
2024-02-08 22:39:10 +05:30
AidanBeltonS
4833ac209d
[SYCL] Fix cpy with dims of 3 (#5289)
* Fix cpy with dims of 3

* rm asserts

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-02-05 12:38:24 +05:30
AidanBeltonS
a305dba8ff
Fix im2col with 32fp (#5286) 2024-02-03 16:11:37 +08:00
AidanBeltonS
b05102fe8c
Tidy ggml-sycl (#5261)
* Tidy some code in ggml-sycl

* Remove blank space

* Remove std::printf comments

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-02-02 16:39:48 +08:00
Meng, Hengyu
e805f0fa99
[SYCL] get MAX_MEM_ALLOC from device property (#5270)
* get max alloc size from device prop

* fix macro typo
2024-02-02 15:54:14 +08:00