Commit Graph

3411 Commits

Author SHA1 Message Date
hutli
d39b308eaf nix: moved blas availability check to package inputs so it is still overridable 2024-03-28 07:48:27 +00:00
hutli
c873976649 using blas.meta.available to check host platform 2024-03-28 07:48:27 +00:00
hutli
dbb03e2b9c only using explicit blas if hostPlatform is allowed 2024-03-28 07:48:27 +00:00
Someone Serge
e9f17dc3bf nix: .#windows: proper cross-compilation set-up
Take all dependencies from the cross stage, rather tha only stdenv
2024-03-28 07:48:27 +00:00
Someone Serge
22a462cc1f nix: package: don't introduce the dependency on python
- The generic /usr/bin/env shebangs are good enough
- Python deps are provisioned in the devShells
- We need to be able to leave python out at least on windows (currently breaks eval)
2024-03-28 07:48:27 +00:00
hutli
f6a0f5c642 nix: .#widnows: init
initial nix build for windows using zig

mingwW64 build

removes nix zig windows build

removes nix zig windows build

removed unnessesary glibc.static

removed unnessesary import of pkgs in nix

fixed missing trailing newline on non-windows nix builds

overriding stdenv when building for crosscompiling to windows in nix

better variables when crosscompiling windows in nix

cross compile windows on macos

removed trailing whitespace

remove unnessesary overwrite of "CMAKE_SYSTEM_NAME" in nix windows build

nix: keep file extension when copying result files during cross compile for windows

nix: better checking for file extensions when using MinGW

nix: using hostPlatform instead of targetPlatform when cross compiling for Windows

using hostPlatform.extensions.executable to extract executable format
2024-03-28 07:48:27 +00:00
Ziang Wu
d0e2f6416b
doc: fix typo in MobileVLM-README.md (#6181) 2024-03-28 13:03:30 +09:00
Neo Zhang Jianyu
25f4a613c4
[SYCL] fix set main gpu crash (#6339) 2024-03-28 08:55:24 +08:00
Pierrick Hymbert
a016026a3a
server: continuous performance monitoring and PR comment (#6283)
* server: bench: init

* server: bench: reduce list of GPU nodes

* server: bench: fix graph, fix output artifact

* ci: bench: add mermaid in case of image cannot be uploaded

* ci: bench: more resilient, more metrics

* ci: bench: trigger build

* ci: bench: fix duration

* ci: bench: fix typo

* ci: bench: fix mermaid values, markdown generated

* typo on the step name

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* ci: bench: trailing spaces

* ci: bench: move images in a details section

* ci: bench: reduce bullet point size

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-03-27 20:26:49 +01:00
Someone Serge
53c7ec53d5 nix: ci: dont test cuda and rocm (for now)
Until https://github.com/ggerganov/llama.cpp/issues/6346 is resolved
2024-03-27 19:18:55 +00:00
slaren
e5b89a441a
ggml : fix bounds checking of zero size views (#6347) 2024-03-27 15:07:50 +01:00
Georgi Gerganov
3a0345970e
make : whitespace 2024-03-27 15:02:49 +02:00
howlger
1e13987fba
embedding : show full embedding for single prompt (#6342)
* embedding : show full embedding for single prompt

To support the use case of creating an embedding for a given prompt, the entire embedding and not just the first part needed to be printed.

Also, show cosine similarity matrix only if there is more than one prompt, as the cosine similarity matrix for a single prompt is always `1.00`.

* Update examples/embedding/embedding.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-27 13:15:44 +02:00
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
Kawrakow
cbc8343619
Make IQ1_M work for QK_K = 64 (#6327)
* iq1_m: make it work for QK_K = 64 (WIP)

* iq1_m: make it work for QK_K = 64 (scalar and AVX2)

* iq1_m: QK_K = 64 seems to work on Metal and ARM_NEON

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-27 08:44:27 +01:00
Sigbjørn Skjæret
e562b9714b
common : change --no-penalize-nl to --penalize-nl (#6334)
* Change --no-penalize-nl to --penalize-nl

* Update documentation too
2024-03-27 09:23:10 +02:00
Georgi Gerganov
2ab4f00d25
llama2c : open file as binary (#6332) 2024-03-27 09:16:02 +02:00
Mateusz Charytoniuk
1740d6dd4e
readme : add php api bindings (#6326)
* add php bindings to readme

* readme : add link to PR

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-27 09:08:59 +02:00
Eric Zhang
0642b22cd1
server: public: use relative routes for static files (#6325)
server: public: support custom `api_url`, default to relative base path
2024-03-27 06:55:29 +01:00
Neo Zhang Jianyu
a4f569e8a3
[SYCL] fix no file in win rel (#6314) 2024-03-27 09:47:06 +08:00
Jared Van Bortel
32c8486e1f
wpm : portable unicode tolower (#6305)
Also use C locale for ispunct/isspace, and split unicode-data.cpp from unicode.cpp.
2024-03-26 17:46:21 -04:00
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
Pedro Cuenca
e097633f63
convert-hf : fix exception in sentencepiece with added tokens (#6320) 2024-03-26 14:32:19 +02:00
Kawrakow
d25b1c31b0
quantize : be able to override metadata by key (#6321)
* quantize: be able to override metadata by key

* minor : spacing

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-26 14:09:30 +02:00
Minsoo Cheong
deb7240100
embedding : adjust n_ubatch value (#6296)
* embedding: assign `n_ubatch` value, print error on `n_batch` overflow

* Update examples/embedding/embedding.cpp

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* use %ld instead of %lld

* Revert "use %ld instead of %lld"

This reverts commit ea753ede90.

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-03-26 11:11:46 +02:00
Jan Boon
3d032ece8e
server : add n_discard parameter (#6300) 2024-03-26 10:47:43 +02:00
Joseph Stahl
e190f1fca6
nix: make xcrun visible in Nix sandbox for precompiling Metal shaders (#6118)
* Symlink to /usr/bin/xcrun so that `xcrun` binary
is usable during build (used for compiling Metal shaders)

Fixes https://github.com/ggerganov/llama.cpp/issues/6117

* cmake - copy default.metallib to install directory

When metal files are compiled to default.metallib, Cmake needs to add this to the install directory so that it's visible to llama-cpp

Also, update package.nix to use absolute path for default.metallib (it's not finding the bundle)

* add `precompileMetalShaders` flag (defaults to false) to disable precompilation of metal shader

Precompilation requires Xcode to be installed and requires disable sandbox on nix-darwin
2024-03-25 17:51:46 -07:00
slaren
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299) 2024-03-26 01:16:01 +01:00
Christian Kögler
b06c16ef9f
nix: fix blas support (#6281)
Since no blas was provided to buildInputs, the executable is built without blas support.

This is a backport of NixOS/nixpkgs#298567
2024-03-25 10:52:45 -07:00
Kawrakow
1f2fd4e727
tests : include IQ2_XXS and IQ2_XS in test-quantize-fns (#6303)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-03-25 19:33:15 +02:00
Georgi Gerganov
43139cc528
flake.lock: Update (#6266)
Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/d691274a972b3165335d261cc4671335f5c67de9' (2024-03-14)
  → 'github:NixOS/nixpkgs/44d0940ea560dee511026a53f0e2e2cde489b4d4' (2024-03-23)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-03-25 08:22:27 -07:00
slaren
2f34b865b6
cuda : fix LLAMA_CUDA_F16 build (#6298) 2024-03-25 16:43:22 +02:00
slaren
ae1f211ce2
cuda : refactor into multiple files (#6269) 2024-03-25 13:50:23 +01:00
Xuan Son Nguyen
ad3a0505e3
Server: clean up OAI params parsing function (#6284)
* server: clean up oai parsing function

* fix response_format

* fix empty response_format

* minor fixes

* add TODO for logprobs

* update docs
2024-03-25 09:42:17 +01:00
Neo Zhang Jianyu
95ad616cdd
[SYCL] fix SYCL backend build on windows is break by LOG() error (#6290)
* fix LOG() error for SYCL, enhance erro check by CI

* rollback to bash

* add newline at end of file
2024-03-25 15:52:41 +08:00
Minsoo Cheong
64e7b47c69
examples : add "retrieval" (#6193)
* add `retrieval` example

* add README

* minor fixes

* cast filepos on print

* remove use of variable sized array

* store similarities in separate vector

* print error on insufficient batch size

* fix error message printing

* assign n_batch value to n_ubatch

* fix param definitions

* define retrieval-only parameters in retrieval.cpp

* fix `--context-file` option to be provided multiple times for multiple files

* use vector for `query_emb`

* add usage description in README

* fix merge conflict

* fix usage printing

* remove seed setting

* fix lint

* increase file read buffer size

* retrieval : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-25 09:38:22 +02:00
Justine Tunney
7733f0c760
ggml : support AVX512VNNI (#6280)
This change causes some quants (e.g. Q4_0, Q8_0) to go faster on some
architectures (e.g. AMD Zen 4).
2024-03-25 07:39:56 +02:00
Rick G
a32b77c4b2
Fix heap corruption from wmode out-of-bound writes on windows (#6272)
* would throw error on VS2022 on GGML_FREE(wmode)
* wchar_t is usually 2 bytes, but malloc wants bytes
  * therefore `*wmode_p++ = (wchar_t)*mode;` could write off the end of the allocation
* Fixes error possibly introduced by https://github.com/ggerganov/llama.cpp/pull/6248
2024-03-24 22:45:56 +01:00
Georgi Gerganov
a0e584defd
imatrix : fix wname for mul_mat_id ops (#6271)
* imatrix : fix wname for mul_mat_id ops

* also filter tensor names in mul_mat_id ops

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-03-24 16:18:45 +02:00
Johannes Gäßler
7aed0ffe68
Fixed lookup compilation issues on Windows (#6273) 2024-03-24 14:21:17 +01:00
Pierrick Hymbert
ea279d5609
ci : close inactive issue, increase operations per run (#6270) 2024-03-24 10:57:06 +02:00
Minsoo Cheong
586e7bc561
sampling : deduplicated code for probability distribution access (#6240)
* sampling: remove duplicated code for probability distribution access

* free original_logits

* fix original_logits allocation

* fixes based on review @cebtenzzre

* change function name to `llama_sampling_prepare`
2024-03-24 10:54:07 +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
Neo Zhang Jianyu
d03224ac98
Support build win release for SYCL (#6241)
* support release win

* fix value

* fix value

* fix value

* fix error

* fix error

* fix format
2024-03-24 09:44:01 +08:00
Jared Van Bortel
94d1b3b411
use _wfopen instead of fopen on Windows (#6248)
also fix missing #defines before windows.h, and BPE LF token on MSVC
2024-03-23 18:48:02 -04:00
Georgi Gerganov
95562175f8
gitignore : gguf-split 2024-03-23 21:35:23 +02:00
Pierrick Hymbert
f482bb2e49
common: llama_load_model_from_url split support (#6192)
* llama: llama_split_prefix fix strncpy does not include string termination
common: llama_load_model_from_url:
 - fix header name case sensitive
 - support downloading additional split in parallel
 - hide password in url

* common: EOL EOF

* common: remove redundant LLAMA_CURL_MAX_PATH_LENGTH definition

* common: change max url max length

* common: minor comment

* server: support HF URL options

* llama: llama_model_loader fix log

* common: use a constant for max url length

* common: clean up curl if file cannot be loaded in gguf

* server: tests: add split tests, and HF options params

* common: move llama_download_hide_password_in_url inside llama_download_file as a lambda

* server: tests: enable back Release test on PR

* spacing

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

* spacing

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

* spacing

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-23 18:07:00 +01:00
Pierrick Hymbert
1997577d5e
server: docs: --threads and --threads, --ubatch-size, --log-disable (#6254) 2024-03-23 18:00:38 +01:00
Julius Arkenberg
476b0251b2
llama : add grok-1 support (#6204)
* Add support for Grok model architecture

* Revert convert-hf-to-gguf to default options

* Fixed f_norm_rms_eps bug

* Fix whitespaces

* llama : fix grok rope type

* llama : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-03-23 18:41:53 +02:00