Commit graph

4289 commits

Author SHA1 Message Date
Eve
c403d895c6 Merge https://github.com/ggerganov/llama.cpp into vulkan 2024-12-04 20:03:31 -05:00
Eve
fe81134954 merge 2024-12-04 20:02:44 -05:00
aryantandon01
f112d198cd
Update deprecation-warning.cpp (#10619)
Fixed Path Separator Handling for Cross-Platform Support (Windows File Systems)
2024-12-04 23:19:20 +01:00
Eve
062f256e6b remove a multiply
polynomial iq4_nl test (slower but keep as reference)
2024-12-04 16:31:14 -05:00
Nicolò Scipione
e147054bf7 SYCL : Move to compile time oneMKL interface backend selection for NVIDIA backend (#10584)
* [SYCL] Move to Compile Time backend selection on oneMKL Interface for NVIDIA backend

Move to compile time selection to backend to avoid latency at run time.
Add it to all mkl gemm calls and only for NVIDIA backend.

Signed-off-by: nscipione <nicolo.scipione@codeplay.com>

* Formatting

* Address PR comments to increase readibility

---------

Signed-off-by: nscipione <nicolo.scipione@codeplay.com>
2024-12-04 16:29:16 -05:00
Wang Ran (汪然)
4153d57c12 fix typo of README.md (#10605) 2024-12-04 16:29:16 -05:00
Frankie Robertson
9075271c95 Avoid using __fp16 on ARM with old nvcc (#10616) 2024-12-04 16:29:16 -05:00
Benson Wong
0a81a82f18 Add docs for creating a static build (#10268) (#10630)
* Add notes for a static build

* Update docs/build.md

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-04 16:29:16 -05:00
piDack
0fa9dc4c06 clip : add sycl support (#10574)
Co-authored-by: piDack <pcdack@hotmail.co>
2024-12-04 16:29:16 -05:00
Jeff Bolz
fa9abd6c82 vulkan: optimize and reenable split_k (#10637)
Use vector loads when possible in mul_mat_split_k_reduce. Use split_k
when there aren't enough workgroups to fill the shaders.
2024-12-04 16:29:16 -05:00
Xuan Son Nguyen
70f0346f0d server : (web ui) Various improvements, now use vite as bundler (#10599)
* hide buttons in dropdown menu

* use npm as deps manager and vite as bundler

* fix build

* fix build (2)

* fix responsive on mobile

* fix more problems on mobile

* sync build

* (test) add CI step for verifying build

* fix ci

* force rebuild .hpp files

* cmake: clean up generated files pre build
2024-12-04 16:29:16 -05:00
Georgi Gerganov
f8fe71abcf scripts : remove amx sync
ggml-ci
2024-12-04 16:29:16 -05:00
Georgi Gerganov
69c7f204df sync : ggml 2024-12-04 16:29:16 -05:00
mahorozte
0df0452af5 CUDA: remove unnecessary warp reduce in FA (ggml/1032)
* kqmax_new_j in every thread within warp is same after operate at line 199,this reduce can be omit

* same problem in vec32

---------

Co-authored-by: ZhaoXiaoYu <zhao.xiaoyu@zte.com.cn>
2024-12-04 16:29:16 -05:00
PAB
2b155906e4 feat: add GGML_UNARY_OP_ARGMAX Metal kernel (ggml/1019)
* implemented argmax kernel

* tpig -> tgpig

* change to strides

* contiguous assertions

* kernel working and tested

* argmax simd parallel implementation

* added 2 new tests for argmax in test-backend-ops

* cosmit

* added 3 tests cases for perf eval

* add test_argmax in make_test_cases_perf

* Update test-backend-ops.cpp

Co-authored-by: Diego Devesa <slarengh@gmail.com>

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-04 16:29:16 -05:00
PAB
e92a46bece metal : add GGML_OP_CONV_TRANSPOSE_1D kernels (ggml/1026)
* wip

* wip implementation f32

* kernel conv transpose 1d f32 working

* initial commit
2024-12-04 16:29:16 -05:00
Xuan Son Nguyen
f697baf88f llama : add missing LLAMA_API for llama_chat_builtin_templates (#10636) 2024-12-04 16:29:16 -05:00
Nikolaos Pothitos
d37b7e0910 readme : add option, update default value, fix formatting (#10271)
* readme : document --no-display-prompt

* readme : update default prompt context size

* readme : remove unnecessary indentation

Indenting a line with four spaces makes Markdown treat that section as
plain text.

* readme : indent commands under bullets

* readme : indent commands in lettered list
2024-12-04 16:29:16 -05:00
Georgi Gerganov
d6753d7068 metal : small-batch mat-mul kernels (#10581)
* metal : small-batch mat-mul kernels

ggml-ci

* metal : add rest of types

ggml-ci

* metal : final adjustments

ggml-ci

* metal : add comments

ggml-ci
2024-12-04 16:29:16 -05:00
Georgi Gerganov
ca7c21358b github : minify link [no ci] (revert)
this doesn't work as expected
2024-12-04 16:29:16 -05:00
Georgi Gerganov
ed8649f8e4 github : minify link [no ci] 2024-12-04 16:29:16 -05:00
Georgi Gerganov
be2d0048f1 server : fix default draft model parameters (#10586)
* server : force F16 KV cache for the draft model

ggml-ci

* server : fix draft params

ggml-ci

* server : various params fixes

ggml-ci
2024-12-04 16:29:16 -05:00
Georgi Gerganov
1da7b76569
server : fix speculative decoding with context shift (#10641)
* server : fix speculative decoding with context shift

ggml-ci

* server : take into account speculative limits

ggml-ci

* server : add tests
2024-12-04 22:38:20 +02:00
Diego Devesa
59f4db1088
ggml : add predefined list of CPU backend variants to build (#10626)
* ggml : add predefined list of CPU backend variants to build

* update CPU dockerfiles
2024-12-04 14:45:40 +01:00
Diego Devesa
2803540814
ggml-cpu : fix HWCAP2_I8MM value (#10646) 2024-12-04 14:40:44 +01:00
ltoniazzi
253b7fde91
Fix HF repo commit to clone lora test models (#10649) 2024-12-04 10:45:48 +01:00
JFLFY2255
8d0cfd554a
llama: Support MiniCPM-1B (with & w/o longrope) (#10559) 2024-12-04 11:42:50 +02:00
Jeff Bolz
2759916d86
vulkan: Implement "fast divide" (mul+shift) for unary ops like copy (#10642) 2024-12-04 08:28:59 +01:00
Nicolò Scipione
40c6d79fb5
SYCL : Move to compile time oneMKL interface backend selection for NVIDIA backend (#10584)
* [SYCL] Move to Compile Time backend selection on oneMKL Interface for NVIDIA backend

Move to compile time selection to backend to avoid latency at run time.
Add it to all mkl gemm calls and only for NVIDIA backend.

Signed-off-by: nscipione <nicolo.scipione@codeplay.com>

* Formatting

* Address PR comments to increase readibility

---------

Signed-off-by: nscipione <nicolo.scipione@codeplay.com>
2024-12-04 09:29:20 +08:00
Wang Ran (汪然)
98036d5670
fix typo of README.md (#10605) 2024-12-04 02:22:50 +01:00
Frankie Robertson
cd2f37b304
Avoid using __fp16 on ARM with old nvcc (#10616) 2024-12-04 01:41:37 +01:00
Benson Wong
da6aac91f1
Add docs for creating a static build (#10268) (#10630)
* Add notes for a static build

* Update docs/build.md

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-04 01:40:36 +01:00
piDack
01e6d9bb71
clip : add sycl support (#10574)
Co-authored-by: piDack <pcdack@hotmail.co>
2024-12-04 01:26:37 +01:00
Jeff Bolz
cc98896db8
vulkan: optimize and reenable split_k (#10637)
Use vector loads when possible in mul_mat_split_k_reduce. Use split_k
when there aren't enough workgroups to fill the shaders.
2024-12-03 20:29:54 +01:00
Xuan Son Nguyen
91c36c269b
server : (web ui) Various improvements, now use vite as bundler (#10599)
* hide buttons in dropdown menu

* use npm as deps manager and vite as bundler

* fix build

* fix build (2)

* fix responsive on mobile

* fix more problems on mobile

* sync build

* (test) add CI step for verifying build

* fix ci

* force rebuild .hpp files

* cmake: clean up generated files pre build
2024-12-03 19:38:44 +01:00
Georgi Gerganov
1cd3df46bd scripts : remove amx sync
ggml-ci
2024-12-03 20:04:49 +02:00
Georgi Gerganov
c505471857 sync : ggml 2024-12-03 20:04:49 +02:00
mahorozte
e9e661bd59 CUDA: remove unnecessary warp reduce in FA (ggml/1032)
* kqmax_new_j in every thread within warp is same after operate at line 199,this reduce can be omit

* same problem in vec32

---------

Co-authored-by: ZhaoXiaoYu <zhao.xiaoyu@zte.com.cn>
2024-12-03 20:04:49 +02:00
PAB
efb6ae9630 feat: add GGML_UNARY_OP_ARGMAX Metal kernel (ggml/1019)
* implemented argmax kernel

* tpig -> tgpig

* change to strides

* contiguous assertions

* kernel working and tested

* argmax simd parallel implementation

* added 2 new tests for argmax in test-backend-ops

* cosmit

* added 3 tests cases for perf eval

* add test_argmax in make_test_cases_perf

* Update test-backend-ops.cpp

Co-authored-by: Diego Devesa <slarengh@gmail.com>

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-03 20:04:49 +02:00
PAB
667d70d170 metal : add GGML_OP_CONV_TRANSPOSE_1D kernels (ggml/1026)
* wip

* wip implementation f32

* kernel conv transpose 1d f32 working

* initial commit
2024-12-03 20:04:49 +02:00
Eve
b7ad234517 dot and delta optimization 2024-12-03 11:57:37 -05:00
Xuan Son Nguyen
3b4f2e33e2
llama : add missing LLAMA_API for llama_chat_builtin_templates (#10636) 2024-12-03 12:54:30 +01:00
Nikolaos Pothitos
82bca2257b
readme : add option, update default value, fix formatting (#10271)
* readme : document --no-display-prompt

* readme : update default prompt context size

* readme : remove unnecessary indentation

Indenting a line with four spaces makes Markdown treat that section as
plain text.

* readme : indent commands under bullets

* readme : indent commands in lettered list
2024-12-03 12:50:08 +02:00
Georgi Gerganov
0115df2f65
metal : small-batch mat-mul kernels (#10581)
* metal : small-batch mat-mul kernels

ggml-ci

* metal : add rest of types

ggml-ci

* metal : final adjustments

ggml-ci

* metal : add comments

ggml-ci
2024-12-03 11:52:33 +02:00
Georgi Gerganov
515d4e5372
github : minify link [no ci] (revert)
this doesn't work as expected
2024-12-03 11:21:43 +02:00
Georgi Gerganov
844e2e1fee
github : minify link [no ci] 2024-12-03 11:20:35 +02:00
Georgi Gerganov
70b98fadbc
server : fix default draft model parameters (#10586)
* server : force F16 KV cache for the draft model

ggml-ci

* server : fix draft params

ggml-ci

* server : various params fixes

ggml-ci
2024-12-03 11:20:00 +02:00
Xuan Son Nguyen
642330ac7c
llama : add enum for built-in chat templates (#10623)
* llama : add enum for supported chat templates

* use "built-in" instead of "supported"

* arg: print list of built-in templates

* fix test

* update server README
2024-12-02 22:10:19 +01:00
Georgi Gerganov
8648c52101
make : deprecate (#10514)
* make : deprecate

ggml-ci

* ci : disable Makefile builds

ggml-ci

* docs : remove make references [no ci]

* ci : disable swift build

ggml-ci

* docs : remove obsolete make references, scripts, examples

ggml-ci

* basic fix for compare-commits.sh

* update build.md

* more build.md updates

* more build.md updates

* more build.md updates

* Update Makefile

Co-authored-by: Diego Devesa <slarengh@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-12-02 21:22:53 +02:00
haopeng
64ed2091b2
server: Add "tokens per second" information in the backend (#10548)
* add cmake rvv support

* add timings

* remove space

* update readme

* fix

* fix code

* remove empty line

* add test

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2024-12-02 14:45:54 +01:00