Commit Graph

2358 Commits

Author SHA1 Message Date
Georgi Gerganov
d55356d3ba cuda : mark I16 and I32 ops as unsupported
ggml-ci
2024-01-03 14:38:38 +02:00
Georgi Gerganov
75e3fd8581 sync : ggml
ggml-ci
2024-01-03 14:38:38 +02:00
Georgi Gerganov
289313716f metal : add kernel_get_rows_i32
ggml-ci
2024-01-03 14:38:38 +02:00
Georgi Gerganov
ab62fc3e55 scripts : fix sync order + metal sed 2024-01-03 14:38:38 +02:00
Guillaume Wenzek
5f66ebca9c ggml : extend ggml_get_rows, ggml_repeat, ggml_concat (ggml/639)
* add more int ops

* ggml_compute_forward_dup_bytes

* add tests

* PR comments

* tests : minor indentations

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-03 14:38:38 +02:00
Justin Parker
f2eb19bd8b
server : throw an error when slot unavailable (#4741) 2024-01-03 10:43:19 +02:00
Georgi Gerganov
f3f62f0d83
metal : optimize ggml_mul_mat_id (faster Mixtral PP) (#4725)
* ggml : disable fast-math for Metal (cmake build only)

ggml-ci

* metal : fix Metal API debug warnings

* cmake : add -fno-inline for Metal build (#4545)

* metal : fix API debug warnings

* metal : fix compile warnings

* metal : use uint64_t for strides

* cmake : rename option to LLAMA_METAL_SHADER_DEBUG

* metal : fix mat-vec Q8_0 kernel for BS > 1

* metal : normalize mat-vec kernel signatures

* cmake : respect LLAMA_QKK_64 option

* metal : fix mat-vec Q4_K kernel for QK_K == 64

* metal : optimizing ggml_mul_mat_id (wip)

* metal : minor fix

* metal : opt mul_mm_id
2024-01-02 21:07:47 +02:00
Phil H
0ef3ca2ac6
server : add token counts to html footer (#4738)
* server: add token counts to stats

* server: generate hpp

---------

Co-authored-by: phiharri <ph@got-root.co.uk>
2024-01-02 17:48:49 +02:00
Georgi Gerganov
540938f890
llama : llama_model_desc print number of experts 2024-01-02 16:26:45 +02:00
Marcus Dunn
0040d42eeb
llama : replace all API facing int's with int32_t (#4577)
* replaced all API facing `int`'s with `int32_t`

* formatting and missed `int` in `llama_token_to_piece`
2024-01-02 16:15:16 +02:00
postmasters
83e633c27e
llama : differentiate the KV dims in the attention (#4657)
* Add n_key_dim and n_value_dim

Some models use values that are not derived from `n_embd`.
Also remove `n_embd_head` and `n_embd_gqa` because it is not clear
which "head" is referred to (key or value).

Fix issue #4648.

* Fix `llm_build_kqv` to use `n_value_gqa`

* Rebase

* Rename variables

* Fix llm_build_kqv to be more generic wrt n_embd_head_k

* Update default values for n_embd_head_k and n_embd_head_v

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

* Fix llm_load_tensors: the asserts were not backcompat

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-02 13:51:28 +02:00
Georgi Gerganov
32866c5edd
editorconfig : fix whitespace and indentation #4710 2024-01-02 13:28:15 +02:00
minarchist
5d7002d437
server : add --override-kv parameter (#4710)
* Changes to server to allow metadata override

* documentation

* flake.nix: expose full scope in legacyPackages

* flake.nix: rocm not yet supported on aarch64, so hide the output

* flake.nix: expose checks

* workflows: nix-ci: init; build flake outputs

* workflows: nix-ci: add a job for eval

* workflows: weekly `nix flake update`

* workflows: nix-flakestry: drop tag filters

...and add a job for flakehub.com

* workflows: nix-ci: add a qemu job for jetsons

* flake.nix: suggest the binary caches

* flake.lock: update

to a commit recently cached by nixpkgs-cuda-ci

---------

Co-authored-by: John <john@jLap.lan>
Co-authored-by: Someone Serge <sergei.kozlukov@aalto.fi>
2024-01-02 12:38:15 +02:00
Nam D. Tran
26f3071d71
py : re-enable mmap in convert hf (#4732)
* update: awq support llama-7b model

* update: change order

* update: benchmark results for llama2-7b

* update: mistral 7b v1 benchmark

* update: support 4 models

* fix: Readme

* update: ready for PR

* update: readme

* fix: readme

* update: change order import

* black

* format code

* update: work for bot mpt and awqmpt

* update: readme

* Rename to llm_build_ffn_mpt_awq

* Formatted other files

* Fixed params count

* fix: remove code

* update: more detail for mpt

* fix: readme

* fix: readme

* update: change folder architecture

* fix: common.cpp

* fix: readme

* fix: remove ggml_repeat

* update: cicd

* update: cicd

* uppdate: remove use_awq arg

* update: readme

* llama : adapt plamo to new ffn

ggml-ci

* fix: update torch version

---------

Co-authored-by: Trần Đức Nam <v.namtd12@vinai.io>
Co-authored-by: Le Hoang Anh <v.anhlh33@vinai.io>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-01-02 11:23:38 +02:00
Daniel Bevenius
775ac8712a
finetune: fix typo in README.md (#4733)
Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-01-02 10:16:55 +01:00
Georgi Gerganov
58ba655af0
metal : enable shader debugging (cmake option) (#4705)
* ggml : disable fast-math for Metal (cmake build only)

ggml-ci

* metal : fix Metal API debug warnings

* cmake : add -fno-inline for Metal build (#4545)

* metal : fix API debug warnings

* metal : fix compile warnings

* metal : use uint64_t for strides

* cmake : rename option to LLAMA_METAL_SHADER_DEBUG

* metal : fix mat-vec Q8_0 kernel for BS > 1

* metal : normalize mat-vec kernel signatures

* cmake : respect LLAMA_QKK_64 option

* metal : fix mat-vec Q4_K kernel for QK_K == 64

ggml-ci
2024-01-02 10:57:44 +02:00
Someone Serge
edd1ab7bc3 flake.lock: update
to a commit recently cached by nixpkgs-cuda-ci
2023-12-31 13:14:58 -08:00
Someone Serge
198ed7ebfc flake.nix: suggest the binary caches 2023-12-31 13:14:58 -08:00
Someone Serge
d836174731 workflows: nix-ci: add a qemu job for jetsons 2023-12-31 13:14:58 -08:00
Someone Serge
06f2a5d190 workflows: nix-flakestry: drop tag filters
...and add a job for flakehub.com
2023-12-31 13:14:58 -08:00
Someone Serge
c5239944ba workflows: weekly nix flake update 2023-12-31 13:14:58 -08:00
Someone Serge
1e9ae54cf2 workflows: nix-ci: add a job for eval 2023-12-31 13:14:58 -08:00
Someone Serge
7adedecbe3 workflows: nix-ci: init; build flake outputs 2023-12-31 13:14:58 -08:00
Someone Serge
356ea17e0f flake.nix: expose checks 2023-12-31 13:14:58 -08:00
Someone Serge
a5c088d8c6 flake.nix: rocm not yet supported on aarch64, so hide the output 2023-12-31 13:14:58 -08:00
Someone Serge
1e3900ebac flake.nix: expose full scope in legacyPackages 2023-12-31 13:14:58 -08:00
Georgi Gerganov
e39106c055
ggml : add ggml_vdotq_s32 alias (#4715)
ggml-ci
2023-12-31 11:43:31 +02:00
Georgi Gerganov
9fbda719de
clip : refactor + bug fixes (#4696)
* clip : refactor + bug fixes

ggml-ci

* server : add log message
2023-12-30 23:24:42 +02:00
Johannes Gäßler
39d8bc71ed
CUDA: fixed tensor cores not being used on RDNA3 (#4697) 2023-12-30 13:52:01 +01:00
automaticcat
24a447e20a
ggml : add ggml_cpu_has_avx_vnni() (#4589)
* feat: add avx_vnni based on intel documents

* ggml: add avx vnni based on intel document

* llama: add avx vnni information display

* docs: add more details about using oneMKL and oneAPI for intel processors

* docs: add more details about using oneMKL and oneAPI for intel processors

* docs: add more details about using oneMKL and oneAPI for intel processors

* docs: add more details about using oneMKL and oneAPI for intel processors

* docs: add more details about using oneMKL and oneAPI for intel processors

* Update ggml.c

Fix indentation upgate

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-30 10:07:48 +02:00
Johannes Gäßler
a20f3c7465
CUDA: fix tensor core logic for Pascal and HIP (#4682) 2023-12-29 23:12:53 +01:00
Georgi Gerganov
0235b9b571
clip : use ggml_backend_buffer_is_host (#4205) 2023-12-29 18:53:34 +02:00
Steward Garcia
ce18d727a4
clip : enable gpu backend (#4205)
* clip: enable CUDA backend

* add missing kernels

* add enough padding for alignment

* remove ggml_repeat of clip.cpp

* add metal backend

* llava : fixes

- avoid ggml_repeat
- use GGML_USE_ instead of CLIP_USE_ macros
- remove unused vars

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-29 18:52:15 +02:00
hydai
91bb39cec7
cuda: fix vmm oom issue on NVIDIA AGX Orin (#4687)
Signed-off-by: hydai <hydai@secondstate.io>
2023-12-29 17:31:19 +01:00
crasm
04ac0607e9
python : add check-requirements.sh and GitHub workflow (#4585)
* python: add check-requirements.sh and GitHub workflow

This script and workflow forces package versions to remain compatible
across all convert*.py scripts, while allowing secondary convert scripts
to import dependencies not wanted in convert.py.

* Move requirements into ./requirements

* Fail on "==" being used for package requirements (but can be suppressed)

* Enforce "compatible release" syntax instead of ==

* Update workflow

* Add upper version bound for transformers and protobuf

* improve check-requirements.sh

* small syntax change

* don't remove venvs if nocleanup is passed

* See if this fixes docker workflow

* Move check-requirements.sh into ./scripts/

---------

Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2023-12-29 16:50:29 +02:00
Philip Taron
68eccbdc5b
flake.nix : rewrite (#4605)
* flake.lock: update to hotfix CUDA::cuda_driver

Required to support https://github.com/ggerganov/llama.cpp/pull/4606

* flake.nix: rewrite

1. Split into separate files per output.

2. Added overlays, so that this flake can be integrated into others.
   The names in the overlay are `llama-cpp`, `llama-cpp-opencl`,
   `llama-cpp-cuda`, and `llama-cpp-rocm` so that they fit into the
   broader set of Nix packages from [nixpkgs](https://github.com/nixos/nixpkgs).

3. Use [callPackage](https://summer.nixos.org/blog/callpackage-a-tool-for-the-lazy/)
   rather than `with pkgs;` so that there's dependency injection rather
   than dependency lookup.

4. Add a description and meta information for each package.
   The description includes a bit about what's trying to accelerate each one.

5. Use specific CUDA packages instead of cudatoolkit on the advice of SomeoneSerge.

6. Format with `serokell/nixfmt` for a consistent style.

7. Update `flake.lock` with the latest goods.

* flake.nix: use finalPackage instead of passing it manually

* nix: unclutter darwin support

* nix: pass most darwin frameworks unconditionally

...for simplicity

* *.nix: nixfmt

nix shell github:piegamesde/nixfmt/rfc101-style --command \
    nixfmt flake.nix .devops/nix/*.nix

* flake.nix: add maintainers

* nix: move meta down to follow Nixpkgs style more closely

* nix: add missing meta attributes

nix: clarify the interpretation of meta.maintainers

nix: clarify the meaning of "broken" and "badPlatforms"

nix: passthru: expose the use* flags for inspection

E.g.:

```
❯ nix eval .#cuda.useCuda
true
```

* flake.nix: avoid re-evaluating nixpkgs too many times

* flake.nix: use flake-parts

* nix: migrate to pname+version

* flake.nix: overlay: expose both the namespace and the default attribute

* ci: add the (Nix) flakestry workflow

* nix: cmakeFlags: explicit OFF bools

* nix: cuda: reduce runtime closure

* nix: fewer rebuilds

* nix: respect config.cudaCapabilities

* nix: add the impure driver's location to the DT_RUNPATHs

* nix: clean sources more thoroughly

...this way outPaths change less frequently,
and so there are fewer rebuilds

* nix: explicit mpi support

* nix: explicit jetson support

* flake.nix: darwin: only expose the default

---------

Co-authored-by: Someone Serge <sergei.kozlukov@aalto.fi>
2023-12-29 16:42:26 +02:00
Cuong Trinh Manh
97bbca6e85
cmake : fix ld warning duplicate libraries libllama.a (#4671)
* fix "ld: warning: ignoring duplicate libraries: '../libllama.a'"

* fix warning in example.
2023-12-29 16:39:15 +02:00
Justine Tunney
4af4801566
llava-cli : refactor to use sampling library (#4669)
This change makes it possible to use flags like `--grammar` when using
the `llava-cli` program. The rest is just code cleanup deleting a long
standing TODO comment.

This change also ensures that logging information is emitted to stderr
which helps the `llava-cli` command be more friendly to shell scripts.

See Mozilla-Ocho/llamafile@1cd334f
2023-12-29 16:38:38 +02:00
Justine Tunney
db49ff8ed7
server : replace sleep with condition variables (#4673)
The server currently schedules tasks using a sleep(5ms) busy loop. This
adds unnecessary latency since most sleep implementations do a round up
to the system scheduling quantum (usually 10ms). Other libc sleep impls
spin for smaller time intervals which results in the server's busy loop
consuming all available cpu. Having the explicit notify() / wait() code
also helps aid in the readability of the server code.

See mozilla-Ocho/llamafile@711344b
2023-12-29 16:24:12 +02:00
SakuraUmi
60f55e888c
server : fix OpenAI server sampling w.r.t. penalty. (#4675) 2023-12-29 16:22:44 +02:00
Karthik Sethuraman
b93edd22f5
server : allow to generate multimodal embeddings (#4681) 2023-12-29 16:22:10 +02:00
andrijdavid
82d6eab224
main-cmake-pkg : fix build issue (#4665)
* Fix main-cmake-pkg compilation

* Use glob to load common files

* cmake : fix trailing whitespace

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-29 16:18:20 +02:00
Peter Sugihara
afd997ab60
llama.swiftui : fix infinite loop, ouput timings, buff UI (#4674)
* fix infinite loop

* slight UI simplification, clearer UX

* clearer UI text, add timings to completion log
2023-12-29 15:58:56 +02:00
Georgi Gerganov
c8255f8a6b
scripts : print list of sync commits 2023-12-29 15:12:35 +02:00
Tamotsu Takahashi
441f51dca0
ci : build with CLBlast + ggml-opencl use GGML_API (whisper/1576)
* Build with CLBlast

* Declare GGML_API

After rebasing, examples/talk-llama failed:

"D:\a\whisper.cpp\whisper.cpp\build\ALL_BUILD.vcxproj" (build target) (1) ->
"D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj" (default target) (14) ->
(Link target) ->
  llama.obj : error LNK2019: unresolved external symbol ggml_cl_free_data referenced in function "public: __cdecl llama_model::~llama_model(void)" (??1llama_model@@QEAA@XZ) [D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj]
  llama.obj : error LNK2019: unresolved external symbol ggml_cl_transform_tensor referenced in function "public: void __cdecl llama_model_loader::load_all_data(struct ggml_context *,void (__cdecl*)(float,void *),void *,struct llama_mlock *)" (?load_all_data@llama_model_loader@@QEAAXPEAUggml_context@@P6AXMPEAX@Z1PEAUllama_mlock@@@Z) [D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj]
  D:\a\whisper.cpp\whisper.cpp\build\bin\Release\talk-llama.exe : fatal error LNK1120: 2 unresolved externals [D:\a\whisper.cpp\whisper.cpp\build\examples\talk-llama\talk-llama.vcxproj]
2023-12-29 15:11:53 +02:00
Georgi Gerganov
38b3de4658
sync : ggml 2023-12-29 14:56:41 +02:00
bssrdf
afc8c19291
ggml : fix some mul mat cases + add tests for src1 F16 (ggml/669)
* fixed mul-mat error for old GPUs

* style fixes

* add mul mat src1 f16 test cases, fix more cases

ggml-ci

---------

Co-authored-by: bssrdf <bssrdf@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
2023-12-29 14:54:19 +02:00
Georgi Gerganov
ca38b8d334
scripts : do not sync commits from this repo 2023-12-29 14:54:05 +02:00
Justine Tunney
65e5f6dadb
Fix OpenAI server sampling w.r.t. temp and seed (#4668)
The default values for tfs_z and typical_p were being set to zero, which
caused the token candidates array to get shrunk down to one element thus
preventing any sampling. Note this only applies to OpenAI API compatible
HTTP server requests.

The solution is to use the default values that OpenAI documents, as well
as ensuring we use the llama.cpp defaults for the rest. I've tested this
change still ensures deterministic output by default. If a "temperature"
greater than 0 is explicitly passed, then output is unique each time. If
"seed" is specified in addition to "temperature" then the output becomes
deterministic once more.

See mozilla-Ocho/llamafile#117
See mozilla-Ocho/llamafile@9e4bf29
2023-12-28 15:20:00 -04:00
manikbhandari
ea5497df5d
gpt2 : Add gpt2 architecture integration (#4555) 2023-12-28 15:03:57 +01:00