Commit Graph

2994 Commits

Author SHA1 Message Date
Georgi Gerganov
8a1756abdf
ggml : do not break cuBLAS build (Q4_3 is not yet implemented) 2023-04-20 21:43:50 +03:00
Georgi Gerganov
66aab46079
ggml : fix Q4_3 quantization
Broke it during conflict resolution in last PR
2023-04-20 20:44:05 +03:00
Kawrakow
38de86a711
llama : multi-threaded quantization (#1075)
* Multi-threading quantization.

Not much gain for simple quantizations, bit it will be important
for quantizations that require more CPU cycles.

* Multi-threading for quantize-stats

It now does the job in ~14 seconds on my Mac for
Q4_0, Q4_1 and Q4_2. Single-threaded it was taking
more than 2 minutes after adding the more elaborate
version of Q4_2.

* Reviewer comments

* Avoiding compiler confusion

After changing chunk_size to const int as suggested by
@ggerganov, clang and GCC starting to warn me that I don't
need to capture it in the lambda. So, I removed it from the
capture list. But that makes the MSVC build fail. So,
making it a constexpr to make every compiler happy.

* Still fighting with lambda captures in MSVC

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-04-20 20:42:27 +03:00
Georgi Gerganov
e0305ead3a
ggml : add Q4_3 quantization (#1082) 2023-04-20 20:35:53 +03:00
Ivan Komarov
6a9661ea5a
ci : remove the LLAMA_ACCELERATE matrix dimension from Ubuntu builds in the CI (#1074)
[Accelerate](https://developer.apple.com/documentation/accelerate) is an Apple framework which can only be used on macOS, and the CMake build [ignores](https://github.com/ggerganov/llama.cpp/blob/master/CMakeLists.txt#L102) the `LLAMA_ACCELERATE` variable when run on non-Apple platforms. This implies setting `LLAMA_ACCELERATE` is a no-op on Ubuntu and can be removed.

This will reduce visual noise in CI check results (in addition to reducing the number of checks we have to run for every PR). Right now every sanitized build is duplicated twice for no good reason (e.g., we have `CI / ubuntu-latest-cmake-sanitizer (ADDRESS, Debug, ON)` and `CI / ubuntu-latest-cmake-sanitizer (ADDRESS, Debug, OFF)`).
2023-04-20 18:15:18 +03:00
源文雨
5addcb120c
fix: LLAMA_CUBLAS=1 undefined reference 'shm_open' (#1080) 2023-04-20 15:28:43 +02:00
Stephan Walter
c8c2c52482
AVX2 optimization for vec_dot_q4_2_q8_0 (#1068) 2023-04-20 08:45:41 +02:00
slaren
02d6988121
Improve cuBLAS performance by dequantizing on the GPU (#1065) 2023-04-20 03:14:14 +02:00
CRD716
834695fe3a
Minor: Readme fixed grammar, spelling, and misc updates (#1071) 2023-04-19 19:52:14 +00:00
Kawrakow
f7d05095b4
Q4_2 quantization with rmse-optimized scale and quants (#1062)
* Q4_2 quantization with rmse-optimized scale and quants

For quantize-stats we get
q4_2: rmse 0.00159301, maxerr 0.17480469, 95pct<0.0030, median<0.0012

For 7B perplexity with BLAS enabled we get 6.2038 after 655 chunks.

Quantization is slow (~90 seconds on my Mac for 7B) as not
multi-threaded as in PR #896.

* ggml : satisfy the sanitizer builds

Not sure why this makes them fail

* Better follow ggml conventions for function names

* Fixed type as per reviewer comment

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-04-19 20:20:14 +02:00
Georgi Gerganov
884e7d7a2b
ggml : use 8-bit precision for Q4_1 intermediate results (#1047)
* ggml : use 8-bit precision for Q4_1 intermediate results (ARM)

* ggml : optimize ggml_vec_dot_q4_1_q8_0() via vmalq_n_f32

56 ms/token with Q4_1 !

* ggml : AVX2 implementation of ggml_vec_dot_q4_1_q8_0 (#1051)

* gitignore : ignore ppl-*.txt files

---------

Co-authored-by: slaren <2141330+slaren@users.noreply.github.com>
2023-04-19 20:10:08 +03:00
Georgi Gerganov
7cd5c4a3e9
readme : add warning about Q4_2 and Q4_3 2023-04-19 19:07:54 +03:00
Stephan Walter
f3d4edf504
ggml : Q4 cleanup - remove 4-bit dot product code (#1061)
* Q4 cleanup

* Remove unused AVX512 Q4_0 code
2023-04-19 19:06:37 +03:00
slaren
8944a13296
Add NVIDIA cuBLAS support (#1044) 2023-04-19 11:22:45 +02:00
slaren
6667401238
Multi-threaded ggml_cpy (#1035)
* Multi-threaded ggml_cpy

* Update ggml.c

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

* Also fix wdata offset in ggml_compute_forward_add_q_f32

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-04-19 00:53:24 +02:00
Georgi Gerganov
77a73403ca
ggml : add new Q4_2 quantization (ARM only) (#1046)
* ggml : Q4_2 ARM

* ggml : add ggml_is_quantized()

* llama : update llama_type_name() with Q4_2 entry

* ggml : speed-up q4_2

- 4 threads: ~100ms -> ~90ms
- 8 threads:  ~55ms -> ~50ms

* ggml : optimize q4_2 using vmlaq_n_f32 + vmulq_n_f32
2023-04-18 23:54:57 +03:00
Georgi Gerganov
50a8a2af97
ggml : scratch that - vmlaq_n_f32 is always better
Had a background process that was messing with the timings
2023-04-18 23:11:23 +03:00
Georgi Gerganov
4caebf6d40
gitignore : vdot 2023-04-18 23:00:08 +03:00
Georgi Gerganov
dcdd65e296
ggml : optimize ggml_vec_dot_q4_0_q8_0() using vectorized accumulators 2023-04-18 22:59:17 +03:00
Kawrakow
5ecff35151
Adding a simple program to measure speed of dot products (#1041)
On my Mac, the direct Q4_1 product is marginally slower
(~69 vs ~55 us for Q4_0). The SIMD-ified ggml version
is now almost 2X slower (~121 us).

On a Ryzen 7950X CPU, the direct product for Q4_1 quantization
is faster than the AVX2 implementation (~60 vs ~62 us).

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-04-18 19:00:14 +00:00
Georgi Gerganov
7faa7460f0
readme : update hot topics about new LoRA functionality 2023-04-18 20:10:26 +03:00
Georgi Gerganov
5af8e32238
ci : do not run on drafts 2023-04-18 19:57:06 +03:00
Ivan Komarov
42747220b4
Do not close file after mmap (Windows version) (#1034) 2023-04-18 03:15:50 +02:00
Atsushi Tatsuma
e9298af389
readme : add Ruby bindings (#1029) 2023-04-17 22:34:35 +03:00
Cameron
4ad73137a1
add 4_0 to default outfile namestr dict (#1031)
this came up when trying to convert the gpt4all-lora-unfiltered-quantized.bin file
2023-04-17 20:26:23 +02:00
slaren
315a95a4d3
Add LoRA support (#820) 2023-04-17 17:28:55 +02:00
Arik Poznanski
efd05648c8
llama : well-defined static initialization of complex objects (#927)
* Replaced static initialization of complex objects with a initialization on first use. This prevents an undefined behavior on program run, for example, crash in Release build, works in Debug build

* replaced use of auto with exact type to avoid using -std=c++14

* Made the assessors functions for static maps be static const
2023-04-17 17:41:53 +03:00
Georgi Gerganov
eb17a026fd
quantize-stats : fix bug in --type argument 2023-04-17 17:31:06 +03:00
Georgi Gerganov
69b740289f
ggml : avoid using ggml_fp16_to_fp32() and ggml_fp32_to_fp16() in ggml.c 2023-04-17 16:16:23 +03:00
Ivan Komarov
f266259ad9
Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933) 2023-04-17 15:10:57 +02:00
slaren
47f61aaa5f
Fix: do not close file on mmap (#1017) 2023-04-16 21:27:38 +02:00
Georgi Gerganov
3173a62eb9
stdout : vertical align outputs for better readibility 2023-04-16 13:59:27 +03:00
Pavol Rusnak
489537e6cf
examples: add missing <ctime> include for time() (#1011) 2023-04-16 10:13:00 +00:00
nanahi
2d3481c721
Fix msys2 build error and warnings (#1009) 2023-04-16 11:13:42 +02:00
comex
74f5899df4
convert.py: Fix loading safetensors and ggml format on Windows (#991)
Calling `mmap.mmap` on Windows apparently resets the file offset of the
raw file object (and makes the BufferedReader return a *negative* file
offset).  For safetensors, avoid using the file offset after calling
mmap.  For GGML format, explicitly save and restore the offset.

Fixes #966.
2023-04-15 23:53:21 +02:00
Stephan Walter
2f7c8e014e
Fix potential int8 overflow in non-SIMD vec_dot (#986) 2023-04-15 18:28:56 +00:00
Stephan Walter
0ad964631f
Refactor ggml.c for future tensor types (#1001) 2023-04-15 16:25:38 +00:00
Georgi Gerganov
e95b6554b4
ggml : add Q8_0 quantization for intermediate results (#951)
* ggml : add Q8_0 quantization for intermediate results

* quantize-stats : fix test + add it to Makefile default

* Q8: use int8_t, AVX/AVX2 optimizations

* ggml : fix quantize_row_q8_0() ARM_NEON rounding

* minor : updates after rebase to latest master

* quantize-stats : delete obsolete strings

* ggml : fix q4_1 dot func

---------

Co-authored-by: Stephan Walter <stephan@walter.name>
2023-04-15 17:53:22 +03:00
Georgi Gerganov
aa485cee33
ggml : use posix_memalign on non-Windows env 2023-04-15 14:25:45 +03:00
Ivan Komarov
c12b14b77f
benchmark : fix result validation in benchmark-q4_0-matmult (#987) 2023-04-15 08:51:54 +03:00
katsu560
106faaf297
cmake : add finding the OpenBLAS header file (#992) 2023-04-15 08:51:11 +03:00
Pavol Rusnak
c85e03d12e
Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)
This reverts commit f4d277ae17.
2023-04-14 22:58:43 +03:00
Pavol Rusnak
489093548c
py : bump sentencepiece to 0.1.98 to support Python 3.11 (#976) 2023-04-14 19:46:49 +00:00
Stephan Walter
93265e988a
make : fix dependencies, use auto variables (#983) 2023-04-14 22:39:48 +03:00
Pavol Rusnak
c56b715269
Expose type name from ggml (#970)
Avoid duplication of type names in utils

Co-authored-by: Håkon H. Hitland <haakon@likedan.net>
2023-04-14 20:05:37 +02:00
Tomáš Pazdiora
f4d277ae17
main : alternative instruct mode (Vicuna support, etc.) (#863)
* Add support for configs, add configurable prefixes / suffixes, deprecate instruct mode, add stop prompt

* Add multiline mode, update text input.

* bugfix

* update implementation

* typos

* Change --multiline implementation to be toggled by EOF.

* bugfix

* default multiline mode

* add more configs

* update formating

* update formatting

* apply suggestions
2023-04-14 18:19:17 +03:00
Kerfuffle
c9a59b70a5
ggml : add unary and binary map operations (#874)
* GGML map ops proof of concept.

* Various cleanups.

Add handling for task setting.

Add handling for ggml_compute_backward.

Rename functions to ggml_map_unary_f32 and ggml_map_binary_f32

Fix compiler warnings related to casting function pointers and `void *`

Reorder functions and definitions based on the GGML op number.

Use typedefs for map op function pointer types.

* Fix position of map ops cases in ggml_compute_forward
2023-04-14 17:43:55 +03:00
Pavol Rusnak
a32f7acc9f
py : cleanup dependencies (#962)
after #545 we do not need torch, tqdm and requests in the dependencies
2023-04-14 15:37:11 +02:00
Pavol Rusnak
43ffdefb74
py : fix flake8 and isort nitpicks (#960) 2023-04-14 14:23:21 +02:00
Georgi Gerganov
1623a6e9b4
ggml : minor 2023-04-14 13:31:29 +03:00