Commit graph

26 commits

Author SHA1 Message Date
Georgi Gerganov
574406dc7e
ggml : add Q5_0 and Q5_1 quantization (#1187)
* ggml : add Q5_0 quantization (cuBLAS only)

* ggml : fix Q5_0 qh -> uint32_t

* ggml : fix q5_0 histogram stats

* ggml : q5_0 scalar dot product

* ggml : q5_0 ARM NEON dot

* ggml : q5_0 more efficient ARM NEON using uint64_t masks

* ggml : rename Q5_0 -> Q5_1

* ggml : adding Q5_0 mode

* quantize : add Q5_0 and Q5_1 to map

* ggml : AVX2 optimizations for Q5_0, Q5_1 (#1195)

---------

Co-authored-by: Stephan Walter <stephan@walter.name>
2023-04-26 23:14:13 +03:00
Ásgeir Bjarni Ingvarsson
87a6f846d3
Allow setting the rng seed after initialization. (#1184)
The llama_set_state_data function restores the rng state to what it
was at the time llama_copy_state_data was called. But users may want
to restore the state and proceed with a different seed.
2023-04-26 22:08:43 +02:00
Georgi Gerganov
7a32fcb3b2
ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)
* ggml : add Q8_0 quantization format (rename the old one to Q8_1)

* tests : fix test-quantize-fns

* ggml : finalize Q8_0 implementation

* ggml : use q4_0_q8_0 and q4_2_q8_0

* ggml : fix Q8_0 dot product bug (ARM)

* ggml : Q8_0 unroll x2

* ggml : fix bug - using wrong block type

* ggml : extend quantize_fns_t with "vec_dot_type"

* ggml : fix Q8_0 to use 255 values out of 256

* ggml : fix assert using wrong QK4_2 instead of QK4_3
2023-04-25 23:40:51 +03:00
Georgi Gerganov
c4fe84fb0d
llama : refactor get / set state + remove redundant kv cache API (#1143) 2023-04-24 07:40:02 +03:00
xaedes
b6e7f9b09e
llama : add api for getting/setting the complete state: rng, logits, embedding and kv_cache (#1105)
* reserve correct size for logits

* add functions to get and set the whole llama state:

including rng, logits, embedding and kv_cache

* remove unused variables

* remove trailing whitespace

* fix comment
2023-04-22 09:21:32 +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
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
slaren
315a95a4d3
Add LoRA support (#820) 2023-04-17 17:28:55 +02:00
Georgi Gerganov
9190e8eac8
llama : merge llama_internal.h into llama.h
Hide it behind an #ifdef
2023-04-13 18:04:45 +03:00
Stephan Walter
e7f6997f89
Don't crash on ftype (formerly f16) == 4 (#917) 2023-04-12 15:06:16 +00:00
Stephan Walter
3e6e70d8e8
Add enum llama_ftype, sync ggml_type to model files (#709) 2023-04-11 15:03:51 +00:00
comex
f963b63afa Rewrite loading code to try to satisfy everyone:
- Support all three formats (ggml, ggmf, ggjt).  (However, I didn't
  include the hack needed to support GPT4All files without conversion.
  Those can still be used after converting them with convert.py from my
  other PR.)

- Support both mmap and read (mmap is used by default, but can be
  disabled with `--no-mmap`, and is automatically disabled for pre-ggjt
  files or on platforms where mmap is not supported).

- Support multi-file models like before, but automatically determine the
  number of parts rather than requiring `--n_parts`.

- Improve validation and error checking.

- Stop using the per-file type field (f16) entirely in favor of just
  relying on the per-tensor type/size fields.  This has no immediate
  benefit, but makes it easier to experiment with different formats, and
  should make it easier to support the new GPTQ-for-LLaMa models in the
  future (I have some work in progress on that front).

- Support VirtualLock on Windows (using the same `--mlock` option as on
  Unix).

    - Indicate loading progress when using mmap + mlock.  (Which led me
      to the interesting observation that on my Linux machine, with a
      warm file cache, mlock actually takes some time, whereas mmap
      without mlock starts almost instantly...)

      - To help implement this, move mlock support from ggml to the
        loading code.

- madvise/PrefetchVirtualMemory support (based on #740)

- Switch from ifstream to the `fopen` family of functions to avoid
  unnecessary copying and, when mmap is enabled, allow reusing the same
  file descriptor for both metadata reads and mmap (whereas the existing
  implementation opens the file a second time to mmap).

- Quantization now produces a single-file output even with multi-file
  inputs (not really a feature as much as 'it was easier this way').

Implementation notes:

I tried to factor the code into more discrete pieces than before.

Regarding code style: I tried to follow the code style, but I'm naughty
and used a few advanced C++ features repeatedly:

- Destructors to make it easier to ensure everything gets cleaned up.

- Exceptions.  I don't even usually use exceptions when writing C++, and
  I can remove them if desired... but here they make the loading code
  much more succinct while still properly handling a variety of errors,
  ranging from API calls failing to integer overflow and allocation
  failure.  The exceptions are converted to error codes at the
  API boundary.)

Co-authored-by: Pavol Rusnak <pavol@rusnak.io> (for the bit I copied from #740)
2023-04-10 01:10:46 +02:00
unbounded
62cfc54f77
Add quantize-stats command for testing quantization (#728)
Command that calculates some statistics over the errors introduced by
quantization, like mean square error, max error and some percentile errors for layer
weights. Should be useful for testing quantization improvements.

Exposes some internal state from ggml and llama for testing
2023-04-08 00:09:18 +02:00
Christian Falch
e986f94829
Added api for getting/setting the kv_cache (#685)
The api provides access methods for retrieving the current memory buffer for the kv_cache and its token number.
It also contains a method for setting the kv_cache from a memory buffer.

This makes it possible to load/save history - maybe support --cache-prompt paramater as well?

Co-authored-by: Pavol Rusnak <pavol@rusnak.io>
2023-04-02 12:23:04 +02:00
Justine Tunney
78ca9838ee Make loading weights 10-100x faster
This is a breaking change that's going to give you three benefits:

1. Your inference commands should load 100x faster
2. You may be able to safely load models 2x larger
3. You can run many concurrent inference processes

This was accomplished by changing the file format so we can mmap()
weights directly into memory without having to read() or copy them
thereby ensuring the kernel can make its file cache pages directly
accessible to our inference processes; and secondly, that the file
cache pages are much less likely to get evicted (which would force
loads to hit disk) because they're no longer competing with memory
pages that were needlessly created by gigabytes of standard i/o.

The new file format supports single-file models like LLaMA 7b, and
it also supports multi-file models like LLaMA 13B. Our Python tool
now merges the foo.1, foo.2, etc. files back into a single file so
that the C++ code which maps it doesn't need to reshape data every
time. That's made llama.cpp so much simpler. Much of its load code
has now been deleted.

Furthermore, this change ensures that tensors are aligned properly
on a 32-byte boundary. That opens the door to seeing if we can get
additional performance gains on some microprocessors, by using ops
that require memory alignment.

Lastly note that both POSIX and the Windows platform are supported

Fixes #91
2023-03-30 12:28:25 -07:00
anzz1
a5c42c4b13
Fix typo in llama.h (#593) 2023-03-29 13:19:29 +00:00
anzz1
7f4c5c6651
llama : fix linkage with mingw (#551)
* Revert 7e53955 (#542)

Still needs to be fixed properly

* Fix linking on mingw32
2023-03-28 21:23:09 +03:00
Stephan Walter
436e561931
all : be more strict about converting float to double (#458)
* Be more strict about converting float to double

* Test equivalence of round, SILU implementations

Test module is commented out in CMakeLists.txt because the tests may
take a long time, depending on how much the compiler optimizes.

* Fix softmax in perplexity.cpp

* all : prefer float over double where appropriate

* perplexity : add <cmath>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-28 19:48:20 +03:00
Stephan Walter
c1f885067c
ggml : introduce structs for the q4 data blocks (#356)
* Introduce structs for the q4 data blocks

* ggml : rename quant struct variables + fix ARM_NEON

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-28 18:56:03 +03:00
Georgi Gerganov
03f7e33560
Cleanup STL headers + fix embedding examples + minor stuff 2023-03-25 20:51:14 +02:00
Jed Fox
58e6c9f36f
Add support for file load progress reporting callbacks (#434)
* File load progress reporting

* Move llama_progress_handler into llama_context_params

* Renames

* Use seekg to find file size instead

* More correct load progress

* Call progress callback more frequently

* Fix typo
2023-03-25 07:26:28 +02:00
Doomsdayrs
36d07532ef
Add missing struct annotation (#483)
`llama_sample_top_p_top_k` was missing the struct annotation on line 126.

This causes a compiler issue when being parsed by the Kotlin C interop generator.

This commit fixes the above issue by adding the struct annotation.
2023-03-25 07:21:24 +02:00
comex
563cdc391d
Support calling mlock() on loaded model data on Linux and macOS (#453)
* Support calling mlock() on loaded model data on Linux and macOS

This is enabled by a new --mlock command line option.

Using mlock() disables swapping and memory compression for the model
data.  Doing so can be useful on systems where the model takes up a
large fraction of system RAM.  In my experience, macOS is quite eager to
start compressing llama.cpp's memory, which then makes it halt for a few
seconds while it decompresses, even with a model that uses "only" 25GB
out of 32GB.

Of course, this comes at the cost of forcing the system to swap or
compress other processes' memory instead, so it needs to be used with
care and shouldn't be enabled by default.

In theory it should be possible to support this on Windows as well using
VirtualLock(), but I'm not much of a Windows user.

* Update llama.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-24 17:19:05 +02:00
Luciano
8d4a855c24
Add embedding mode with arg flag. Currently working (#282)
* working but ugly

* add arg flag, not working on embedding mode

* typo

* Working! Thanks to @nullhook

* make params argument instead of hardcoded boolean. remove useless time check

* start doing the instructions but not finished. This probably doesnt compile

* Embeddings extraction support

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-03-24 17:05:13 +02:00
Georgi Gerganov
f5a77a629b
Introduce C-style API (#370)
* Major refactoring - introduce C-style API

* Clean up

* Add <cassert>

* Add <iterator>

* Add <algorithm> ....

* Fix timing reporting and accumulation

* Measure eval time only for single-token calls

* Change llama_tokenize return meaning
2023-03-22 07:32:36 +02:00