Commit Graph

59 Commits

Author SHA1 Message Date
Georgi Gerganov
9506267ce5 ggml : try fix ppc64 (#0) 2024-05-13 11:02:26 +03:00
Hong Bo PENG
40aeeeecc4 ggml : optimize for ppc64le using VSX intrinsics (ggml/784)
* optimize for ppc64le using VSX intrinsics

* 1. code clean up by removing comments about overflow concern.

2. fix typo in suffix of scaling.

* Continue to fix typo in suffix of scaling for QK_K <> 256

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-05-13 11:02:26 +03:00
Justine Tunney
a2ad810118 ggml : introduce bfloat16 support (llama/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
2024-05-13 11:02:26 +03:00
slaren
9d4c8b8aa5 add basic tensor data validation function (llama/6884)
* add basic tensor data validation function

* add --check-tensors command line argument

tensor validation is disabled by default and can be enabled by adding
`--check-tensors` to the command line arguments.

quantize always validates tensors.
2024-05-13 11:02:26 +03:00
Georgi Gerganov
a15fb5cd79 ggml : fix MIN / MAX macros (llama/6904)
ggml-ci
2024-05-13 11:02:26 +03:00
Georgi Gerganov
63fd148d8f ggml : move 32-bit arm compat in ggml-impl.h (llama/6865)
ggml-ci
2024-05-13 11:02:26 +03:00
Justine Tunney
7a4f7d825e ggml : add llamafile sgemm (llama/6414)
This change upstreams llamafile's cpu matrix multiplication kernels
which improve image and prompt evaluation speed. For starters, Q4_0
and Q8_0 weights should go ~40% faster on CPU. The biggest benefits
are with data types like f16 / f32, which process prompts 2x faster
thus making them faster than quantized data types for prompt evals.

This change also introduces bona fide AVX512 support since tinyBLAS
is able to exploit the larger register file. For example, on my CPU
llama.cpp llava-cli processes an image prompt at 305 tokens/second,
using the Q4_K and Q4_0 types, which has always been faster than if
we used f16 LLaVA weights, which at HEAD go 188 tokens/second. With
this change, f16 LLaVA performance leap frogs to 464 tokens/second.

On Intel Core i9-14900K this change improves F16 prompt perf by 5x.
For example, using llama.cpp at HEAD with Mistral 7b f16 to process
a 215 token prompt will go 13 tok/sec. This change has fixes making
it go 52 tok/sec. It's mostly thanks to my vectorized outer product
kernels but also because I added support for correctly counting the
number of cores on Alderlake, so the default thread count discounts
Intel's new efficiency cores. Only Linux right now can count cores.

This work was sponsored by Mozilla who's given permission to change
the license of this code from Apache 2.0 to MIT. To read more about
what's improved, and how it works, see: https://justine.lol/matmul/
2024-05-13 11:02:26 +03:00
Borislav Stanimirov
8dcefdf4a9 build: fix and ignore msvc warnings (ggml/805) 2024-05-13 11:02:26 +03:00
Carolinabanana
526332873b
llama : add Command R Plus support (llama/6491)
* Add Command R Plus GGUF

* Add Command R Plus GGUF

* Loading works up to LayerNorm2D

* Export new tensors in 1D so they are not quantized.

* Fix embedding layer based on Noeda's example

* Whitespace

* Add line

* Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda)

* dranger003: Fix block index overflow in CUDA dequantizing.

* Reverted blocked multiplication code as it still has issues and could affect other Llama arches

* export norms as f32

* fix overflow issues during quant and other cleanup

* Type convention

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

* dranger003: Fix more int overflow during quant.

---------

Co-authored-by: S <seast@Ss-Mac-Studio.local>
Co-authored-by: S <s@example.com>
Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-04-09 20:26:18 +03:00
Georgi Gerganov
2948c740a2
sync : ggml (#2001)
* sync : update scripts

* sync : ggml

* talk-llama : sync llama.cpp

* make : WHISPER_CUBLAS -> WHISPER_CUDA

* ci : try to fix sycl build

* talk-llama : fix make build
2024-03-27 18:55:10 +02:00
Georgi Gerganov
46e3c3f112
ggml : reuse quantum structs across backends (llama/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
2024-03-15 14:01:13 +02:00
Georgi Gerganov
ef24ae0c7d
ggml : fix UB in IQ2_S and IQ3_S (llama/6012) 2024-03-15 14:01:13 +02:00
Kawrakow
9dc60fc02d
1.5 bit: we can do even better (llama/5999)
* iq1_s: we can do even better

Spent one of the 4 scale bits on a signs of a 0.125 shift.
I.e., quants are now -1 + delta, delta, 1 + delta, where delta
is +/- 0.125.

CUDA works, same performance as before.
PPL(LLaMA-v2-7B) is now 11.85!

* iq1_s: make scalar and AVX2 work with the new version

* iq1_s: make Neon work with new version.

~10% drop in performance, so will need some more work.

* iq1_s: make Metal work with new version

* iq1_s: very slightly faster dequantize on Metal

* iq1_s: fix dequantize on the CPU

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-15 14:01:13 +02:00
Michael Podvitskiy
d73a63629e
ggml, ci : Windows ARM runner and build fixes (llama/5979)
* windows arm ci

* fix `error C2078: too many initializers` with ggml_vld1q_u32 macro for MSVC ARM64

* fix `warning C4146: unary minus operator applied to unsigned type, result still unsigned`

* fix `error C2065: '__fp16': undeclared identifier`
2024-03-15 14:01:13 +02:00
Kawrakow
f79d0d4f74
Better 1.5 bit quantization (llama/5971)
* Trying blocvks of 16 for IQ1_S - seems slightly better

* iq1s_blocks16: Adjust scale fudge factor to 1.125

* iq1s_blocks16: going to blocks of 32

with 2048 lattice points, so same bpw.
This is even better than blocks of 16.
Should I try blocks of 64? But to keep the same
bpw, when I go to 4096 lattice points, I need to
remove blocks alltogether and just have superblocks of
256 weights.

* iq1s_blocks16: Use 2*<x^2> as sigma2 in weight adjustment

* iq1s_blocks16: scalar and AVX2 dot products

* iq1s_blocks16: CUDA dot product

* iq1s_blocks16: Metal works, Neon does not

Metal works but TG is dog slow (35 t/s). PP is OKish (493 t/s).
Not seeing the bug in the Neon implementation for now.

* iq1s_blocks16: fixed Neon

* iq1s_blocks16: very slightly faster TG on Metal

Still pathetic at 37 t/s

* iq1s_blocks16: speedup Metal by packing codebook into uint32_t's

* Formatting

* iq1s_blocks16: uint32_t codebook is also better in CUDA

TG-128 is now 204 t/s up from 194 t/s.
PP-512 is 5890 t/s, so significantly better than other quants

* iq1s_blocks16: slightly faster Neon dot product

* iq1s_blocks16: faster AVX2 dot product

* iq1s_blocks16: adjust to ggml-common.h

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-15 14:01:12 +02:00
Georgi Gerganov
653d2e8ff9
ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) (llama/5951) 2024-03-15 14:01:12 +02:00
Georgi Gerganov
2fef660d0a
ggml : remove old quantization functions (llama/5942)
* ggml : remove old quantization functions

ggml-ci

* ggml : simplify ggml_quantize_chunk

ggml-ci

* ggml : restrict correctness

ggml-ci

* ggml : remove hist data from the quantization API

ggml-ci

* tests : remove hist usage in test-backend-ops

ggml-ci

* vulkan : remove hist and fix typo
2024-03-15 14:01:12 +02:00
Georgi Gerganov
24eba5a2ff
ggml : add ggml-common.h to deduplicate shared code (llama/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
2024-03-15 14:01:12 +02:00
Georgi Gerganov
ce945b50c3
ggml : try fix 32-bit arm compat (#1938)
* ggml : try fix 32-bit arm compat

* ggml : fix cont
2024-03-08 23:45:07 +02:00
bobqianic
2f6f1d4465
ggml : use uint8x16_t return type for ggml_vqtbl1q_u8 (llama/5894)
* use uint8x16_t

* Update ggml-quants.c
2024-03-08 11:38:33 +02:00
Jared Van Bortel
8edfc54c2b
quants : use MM256_SET_M128I consistently to fix gcc 7 build (llama/5889) 2024-03-08 11:38:33 +02:00
Georgi Gerganov
bd26876267
ggml : fix IQ3_S AVX implementation (llama/5834)
ggml-ci
2024-03-08 11:38:32 +02:00
Kawrakow
21d295180d
ggml : IQ3_S improvements (llama/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>
2024-03-08 11:38:32 +02:00
Kawrakow
2533305596
ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (llama/5760)
* WIP: make i-quants work for QK_K = 64

* iq2_xs: attempt to fix AVX dot product for QK_K = 64

Tests pass, but I get gibberish.

* QK_K = 64 tests pass on ARM_NEON and Metal

Sadly, that does not mean it actually works.

* Make CUDA compile with QK_K = 64

Tests don't pass, plus we get misaligned access

* Q2_K: fixed bug in imatrix quantization for QK_K = 64

* iq1_s: turn off SIMD implementation for QK_K = 64 (it does not work)

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-28 13:00:30 +02:00
Kawrakow
0eca512ac8
Attempt to fix android build (llama/5752)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-28 13:00:30 +02:00
Kawrakow
013e394a4b
IQ4_XS: a 4.25 bpw quantization (llama/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>
2024-02-28 13:00:29 +02:00
Engininja2
1c71816eab
ggml-quants : fix avx2 iq1_s vec_dot when compiled with gcc (llama/5742) 2024-02-28 13:00:29 +02:00
Kawrakow
7b1d8ea7e0
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (llama/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>
2024-02-28 13:00:29 +02:00
Radosław Gryta
72849c24ba
ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (llama/5711)
* [ggml-quants] Provide ggml_vqtbl1q_u8 for 64bit compatibility

vqtbl1q_u8 is not part of arm v7 neon library

* [android-example] Remove abi filter after arm v7a fix

* [github-workflows] Do not skip Android armeabi-v7a build
2024-02-28 13:00:28 +02:00
Kawrakow
9e7c5212a1
IQ3_S: a much better alternative to Q3_K (llama/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>
2024-02-25 19:58:46 +02:00
Georgi Gerganov
e5d06cfc0f
ggml : always define ggml_fp16_t as uint16_t (llama/5666)
* ggml : always define ggml_fp16_t as uint16_t

ggml-ci

* ggml : cont

ggml-ci

* ggml : cont

* ggml : cont

ggml-ci

* ggml : cont

ggml-ci

* cuda : no longer ggml headers last

ggml-ci

* ggml : fix q6_K FP16 -> FP32 conversion

ggml-ci

* ggml : more FP16 -> FP32 conversion fixes

ggml-ci
2024-02-22 23:25:33 +02:00
Georgi Gerganov
5fdb27ff80
ggml : 32-bit arm compat (#1891)
* ggml : 32-bit arm compat

* ggml : add ggml_vqtbl1q_s8 impl

* ggml : cont
2024-02-22 18:31:40 +02:00
Georgi Gerganov
ce411498f6
sync : llama.cpp (ggml/0)
ggml-ci
2024-02-22 15:12:36 +02:00
Georgi Gerganov
f04e6b87d7
ggml : restore vec dot stride arg names (llama/5453) 2024-02-19 15:53:24 +02:00
Georgi Gerganov
0c33928b55
ci : fix wikitext url + compile warnings (llama/5569)
ggml-ci
2024-02-19 15:53:24 +02:00
Kawrakow
2c1ad21ba8
1.5 bit quantization (llama/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>
2024-02-19 15:53:23 +02:00
Kawrakow
4f5c46a84f
ggml-quants : fix compiler warnings (shadow variable) (llama/5472)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-19 15:53:22 +02:00
Georgi Gerganov
3cc6e04a52
ggml : fix compile warnings (unused vars) (llama/4966) 2024-02-12 09:31:11 +02:00
snadampal
b7ef178b9c
ggml : add mmla kernels for quantized GEMM (llama/4966)
* ggml: aarch64: implement smmla kernel for q8_0_q8_0 quantized gemm

armv8.2-a and above supports MMLA instructions that have higher
throughput than DOT. this commit adds mmla kernel for
q8_0_q8_0 gemm. The feature is enabled if the platform supports
"__ARM_FEATURE_MATMUL_INT8"

On AWS Graviton3 processors this kernel resulted up to 1.5x
improvement for prompt evaluation throughput compared to the
default sdot kernel.

* ggml: aarch64: implement smmla kernel for q4_0_q8_0 quantized gemm

armv8.2-a and above supports MMLA instructions that have higher
throughput than DOT. this commit adds mmla kernel for
q4_0_q8_0 gemm. The feature is enabled if the platform supports
"__ARM_FEATURE_MATMUL_INT8"

On AWS Graviton3 processors this kernel resulted up to 1.5x
improvement for prompt evaluation throughput compared to the
default sdot kernel.

* ggml: aarch64: implement smmla kernel for q4_1_q8_1 quantized gemm

armv8.2-a and above supports MMLA instructions that have higher
throughput than DOT. this commit adds mmla kernel for
q4_1_q8_1 gemm. The feature is enabled if the platform supports
"__ARM_FEATURE_MATMUL_INT8"

On AWS Graviton3 processors this kernel resulted up to 1.5x
improvement for prompt evaluation throughput compared to the
default sdot kernel.

* ggml: update unit tests for the new vec_dot interface

* llama.cpp: add MATMUL_INT8 capability to system_info
2024-02-12 09:31:11 +02:00
Michael Podvitskiy
b6d2827914
ggml : fix error C2078: too many initializers for MSVC ARM64 (llama/5404) 2024-02-10 09:55:47 +02:00
Kawrakow
b562fff9d0
Slight quantization improvement for Q4_K and Q5_K (llama/5361)
* Q4_K: slightly better quantization

* Q5_K: slightly better quantization

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-10 09:55:47 +02:00
Kawrakow
0ed762d691
iq2_xxs: tune quantization (llama/5320)
We get slightly better PPL, and we cut quantization time in
nearly half.

The trick is to 1st quantize without forcing points onto the E8-lattice.
We can then use a narrower search range around the block scale that we
got that way.

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-02-10 09:55:46 +02:00
Kawrakow
98ae5276b7
Faster AVX2 dot product for IQ2_XS (llama/5187)
* iq2xs: faster AVX2 dot product

* iq2xs: small AVX2 imrovement

* Speed up computing sign bits in AVX2 iq2_xs dot product

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Peter Reid <peter@peterreid.net>
2024-01-30 21:27:59 +02:00
Kawrakow
6adb969b09
SOTA 3-bit quants (llama/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 21:27:59 +02:00
Georgi Gerganov
4aea058e5a
ggml : add IQ2 to test-backend-ops + refactoring (llama/4990)
* ggml : add IQ2 to test-backend-ops + refactoring

ggml-ci

* cuda : update supports_op for IQ2

ggml-ci

* ci : enable LLAMA_CUBLAS=1 for CUDA nodes

ggml-ci

* cuda : fix out-of-bounds-access in `mul_mat_vec_q`

ggml-ci

* tests : avoid creating RNGs for each Q tensor

ggml-ci

* tests : avoid creating RNGs for each tensor

ggml-ci
2024-01-17 21:21:10 +02:00
Kawrakow
01637e1a4c
ggml : importance matrix support for legacy quants (llama/4969)
* imatrix: adding support for legacy quants

* imatrix: guard Q4_0/Q5_0 against ffn_down craziness

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-17 21:21:10 +02:00
Kawrakow
f904b31a7d
Add ability to use importance matrix for all k-quants (llama/4930)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-17 21:21:09 +02:00
Kawrakow
dabc964d83
2-bit quantizations (llama/4897)
* imatrix: load

* imatrix: WIP

* imatrix: Add Q2_K quantization

* imatrix: also guard against Q2_K_S quantization without importance matrix

* imatrix: guard even more against low-bit quantization misuse

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-14 10:54:09 +02:00
Georgi Gerganov
6dcee35129
ggml : fix 32-bit ARM compat for IQ2_XS (#1758)
* ggml : fix 32-bit ARM compat

* ggml : fix fix

* ggml : fix fix fix
2024-01-12 14:02:30 +02:00
Kawrakow
97b12212dd
ggml : SOTA 2-bit quants (add IQ2_XS) (llama/4856)
* iq2_xs: basics

* iq2_xs: this should have been in the basics

* iq2_xs: CUDA and scalar CPU works

* iq2_xs: WIP Metal

* iq2_xs: Metal now works

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

* iq2_xs: better ARM_NEON dot product

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

* iq2_xs: AVX2 dot product - 19.5 t/s

* iq2_xs: faster AVX2 dit product

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

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

* Add llama enum for IQ2_XS

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-01-11 21:50:01 +02:00