]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/log
pkg/ggml/sources/llama.cpp
6 months agometal : add `GGML_OP_CONV_TRANSPOSE_1D` kernels (ggml/1026)
PAB [Thu, 28 Nov 2024 08:25:06 +0000 (09:25 +0100)]
metal : add `GGML_OP_CONV_TRANSPOSE_1D` kernels (ggml/1026)

* wip

* wip implementation f32

* kernel conv transpose 1d f32 working

* initial commit

6 months agollama : add missing LLAMA_API for llama_chat_builtin_templates (#10636)
Xuan Son Nguyen [Tue, 3 Dec 2024 11:54:30 +0000 (12:54 +0100)]
llama : add missing LLAMA_API for llama_chat_builtin_templates (#10636)

6 months agoreadme : add option, update default value, fix formatting (#10271)
Nikolaos Pothitos [Tue, 3 Dec 2024 10:50:08 +0000 (12:50 +0200)]
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

6 months agometal : small-batch mat-mul kernels (#10581)
Georgi Gerganov [Tue, 3 Dec 2024 09:52:33 +0000 (11:52 +0200)]
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

6 months agogithub : minify link [no ci] (revert)
Georgi Gerganov [Tue, 3 Dec 2024 09:21:43 +0000 (11:21 +0200)]
github : minify link [no ci] (revert)

this doesn't work as expected

6 months agogithub : minify link [no ci]
Georgi Gerganov [Tue, 3 Dec 2024 09:20:35 +0000 (11:20 +0200)]
github : minify link [no ci]

6 months agoserver : fix default draft model parameters (#10586)
Georgi Gerganov [Tue, 3 Dec 2024 09:20:00 +0000 (11:20 +0200)]
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

6 months agollama : add enum for built-in chat templates (#10623)
Xuan Son Nguyen [Mon, 2 Dec 2024 21:10:19 +0000 (22:10 +0100)]
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

6 months agomake : deprecate (#10514)
Georgi Gerganov [Mon, 2 Dec 2024 19:22:53 +0000 (21:22 +0200)]
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 <redacted>
---------

Co-authored-by: slaren <redacted>
6 months agoserver: Add "tokens per second" information in the backend (#10548)
haopeng [Mon, 2 Dec 2024 13:45:54 +0000 (21:45 +0800)]
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 <redacted>
6 months agoSYCL: Fix and switch to GGML_LOG system instead of fprintf (#10579)
Akarshan Biswas [Mon, 2 Dec 2024 07:04:11 +0000 (12:34 +0530)]
SYCL: Fix and switch to GGML_LOG system instead of fprintf (#10579)

* Switched to GGML_LOG

* Fix missing semicolon

6 months agocontrib : refresh (#10593)
Georgi Gerganov [Mon, 2 Dec 2024 06:53:27 +0000 (08:53 +0200)]
contrib : refresh (#10593)

* contrib : refresh

* contrib : expand [no ci]

* contrib : expand test-backend-ops instructions

* contrib : add CODEOWNERS

* prs : update template to not have checkbox [no ci]

6 months agoAdd `mistral-v1`, `mistral-v3`, `mistral-v3-tekken` and `mistral-v7` chat template...
Juk Armstrong [Sun, 1 Dec 2024 22:09:49 +0000 (22:09 +0000)]
Add `mistral-v1`, `mistral-v3`, `mistral-v3-tekken` and `mistral-v7` chat template types (#10572)

* Templates: `mistral-v1`, `mistral-v2`, `mistral-v3`, `mistral-v3-tekken`

* Changed system message logic and added tests for all 4

* Invalid `system_message` instead of `content` fixed

* Removed tab-indented lines

* Added template code and test for `mistral-v7`

* Added all tests. Fixed bug with `tmpl == "llama2"` test.

* Replaced tabs with spaces.

* Removed `'mistral-v2'` option as no (open) models ever used it

* Removed all references to 'v2' template from comments

* Update llama.cpp

Fixed `trim_assistant_message` bug

6 months agogrammars : add English-only grammar (#10612)
Georgi Gerganov [Sun, 1 Dec 2024 19:37:54 +0000 (21:37 +0200)]
grammars : add English-only grammar (#10612)

6 months agoci: add error handling for Python venv creation in run.sh (#10608)
Wang Qin [Sun, 1 Dec 2024 18:11:42 +0000 (10:11 -0800)]
ci: add error handling for Python venv creation in run.sh (#10608)

6 months agoggml : automatic selection of best CPU backend (#10606)
Diego Devesa [Sun, 1 Dec 2024 15:12:41 +0000 (16:12 +0100)]
ggml : automatic selection of best CPU backend (#10606)

* ggml : automatic selection of best CPU backend

* amx : minor opt

* add GGML_AVX_VNNI to enable avx-vnni, fix checks

6 months agoserver : bind to any port when specified (#10590)
alek3y [Sun, 1 Dec 2024 11:33:12 +0000 (12:33 +0100)]
server : bind to any port when specified (#10590)

6 months agoreadme : update the usage section with examples (#10596)
Georgi Gerganov [Sun, 1 Dec 2024 09:25:17 +0000 (11:25 +0200)]
readme : update the usage section with examples (#10596)

* readme : update the usage section with examples

* readme : more examples

6 months agobuild: update Makefile comments for C++ version change (#10598)
Wang Qin [Sun, 1 Dec 2024 03:19:44 +0000 (19:19 -0800)]
build: update Makefile comments for C++ version change (#10598)

6 months agoggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0...
Adrien Gallouët [Sat, 30 Nov 2024 17:13:18 +0000 (18:13 +0100)]
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0() (#10567)

Signed-off-by: Adrien Gallouët <redacted>
6 months agoreadme : remove old badge
Georgi Gerganov [Sat, 30 Nov 2024 08:09:21 +0000 (10:09 +0200)]
readme : remove old badge

6 months agoreadme : refresh (#10587)
Georgi Gerganov [Sat, 30 Nov 2024 07:47:07 +0000 (09:47 +0200)]
readme : refresh (#10587)

* readme : refresh

* readme : move section [no ci]

* readme : clarify [no ci]

* readme : fixes [no ci]

* readme : more fixes [no ci]

* readme : simplify [no ci]

* readme : clarify GGUF

6 months agovulkan: Dynamic subgroup size support for Q6_K mat_vec (#10536)
Eve [Sat, 30 Nov 2024 07:00:02 +0000 (07:00 +0000)]
vulkan: Dynamic subgroup size support for Q6_K mat_vec (#10536)

* subgroup 64 version with subgroup add. 15% faster

scalable version

tested for subgroup sizes 16-128

* check for subgroup multiple of 16 and greater than 16

* subgroup sizes are always a power of 2 (https://github.com/KhronosGroup/GLSL/issues/45)

* force 16 sequential threads per block

* make 16 subgroup size a constant

6 months agoggml : move AMX to the CPU backend (#10570)
Diego Devesa [Fri, 29 Nov 2024 20:54:58 +0000 (21:54 +0100)]
ggml : move AMX to the CPU backend (#10570)

* ggml : move AMX to the CPU backend

---------

Co-authored-by: Georgi Gerganov <redacted>
6 months agoserver : add more test cases (#10569)
Xuan Son Nguyen [Fri, 29 Nov 2024 20:48:56 +0000 (21:48 +0100)]
server : add more test cases (#10569)

* server : add split model test

* add test speculative

* add invalid cases

6 months agoimatrix : support combine-only (#10492)
Robert Collins [Fri, 29 Nov 2024 17:21:37 +0000 (12:21 -0500)]
imatrix : support combine-only (#10492)

* imatrix-combine-only idea

* ensured that behavior consistent with log

6 months agocleanup UI link list (#10577)
Diego Devesa [Fri, 29 Nov 2024 16:45:08 +0000 (17:45 +0100)]
cleanup UI link list (#10577)

* cleanup UI link list

* sort list alphabetically

* add missing licenses

6 months agoggml : fix I8MM Q4_1 scaling factor conversion (#10562)
Georgi Gerganov [Fri, 29 Nov 2024 14:25:39 +0000 (16:25 +0200)]
ggml : fix I8MM Q4_1 scaling factor conversion (#10562)

ggml-ci

6 months agoggml-cpu: fix typo in gemv/gemm iq4_nl_4_4 (#10580)
Shupei Fan [Fri, 29 Nov 2024 13:49:02 +0000 (21:49 +0800)]
ggml-cpu: fix typo in gemv/gemm iq4_nl_4_4 (#10580)

6 months agosycl : offload of get_rows set to 0 (#10432)
Alberto Cabrera Pérez [Fri, 29 Nov 2024 12:38:45 +0000 (12:38 +0000)]
sycl : offload of get_rows set to 0 (#10432)

6 months agosycl : Reroute permuted mul_mats through oneMKL (#10408)
Alberto Cabrera Pérez [Fri, 29 Nov 2024 09:49:43 +0000 (09:49 +0000)]
sycl : Reroute permuted mul_mats through oneMKL (#10408)

This PR fixes the failing MUL_MAT tests for the sycl backend.

6 months agoCANN: RoPE operator optimization (#10563)
Chenguang Li [Fri, 29 Nov 2024 06:46:55 +0000 (14:46 +0800)]
CANN: RoPE operator optimization (#10563)

* [cann] RoPE operator optimization

* [CANN]Code Formatting

---------

Co-authored-by: noemotiovon <redacted>
6 months agovulkan: get the first command buffer submitted sooner (#10499)
Jeff Bolz [Fri, 29 Nov 2024 06:18:02 +0000 (00:18 -0600)]
vulkan: get the first command buffer submitted sooner (#10499)

This is an incremental improvement over #9118 to get work to the GPU a bit
sooner. The first part is to start with a smaller number of nodes before
the first submit, and ramp it up to the current 100 nodes/submit. The
second part is to reduce the dryrun overhead for all the nodes that just
need to request descriptor space.

With these changes I get around 1-2% speedup on RTX 4070 combined with my
old Haswell-era CPU.

6 months agollava: return false instead of exit (#10546)
Ting Lou [Fri, 29 Nov 2024 00:09:46 +0000 (08:09 +0800)]
llava: return false instead of exit (#10546)

6 months agoggml : remove redundant copyright notice + update authors
Georgi Gerganov [Thu, 28 Nov 2024 18:46:40 +0000 (20:46 +0200)]
ggml : remove redundant copyright notice + update authors

6 months agollama : add missing model types
Georgi Gerganov [Thu, 28 Nov 2024 18:45:07 +0000 (20:45 +0200)]
llama : add missing model types

6 months agoserver : (tests) don't use thread for capturing stdout/stderr, bump openai client...
Xuan Son Nguyen [Thu, 28 Nov 2024 18:17:49 +0000 (19:17 +0100)]
server : (tests) don't use thread for capturing stdout/stderr, bump openai client library (#10568)

* server : (tests) don't use thread for capturing stdout/stderr

* test: bump openai to 1.55.2

* bump openai to 1.55.3

6 months agocommon: fix warning message when no GPU found (#10564)
Johannes Gäßler [Thu, 28 Nov 2024 17:15:25 +0000 (18:15 +0100)]
common: fix warning message when no GPU found (#10564)

6 months agodocs: fix outdated usage of llama-simple (#10565)
Random Fly [Thu, 28 Nov 2024 15:03:11 +0000 (23:03 +0800)]
docs: fix outdated usage of llama-simple (#10565)

6 months agoci : fix tag name in cuda and hip releases (#10566)
Diego Devesa [Thu, 28 Nov 2024 14:58:54 +0000 (15:58 +0100)]
ci : fix tag name in cuda and hip releases (#10566)

7 months agoggml : fix row condition for i8mm kernels (#10561)
Georgi Gerganov [Thu, 28 Nov 2024 12:56:37 +0000 (14:56 +0200)]
ggml : fix row condition for i8mm kernels (#10561)

ggml-ci

7 months agocmake : fix ARM feature detection (#10543)
Georgi Gerganov [Thu, 28 Nov 2024 12:56:23 +0000 (14:56 +0200)]
cmake : fix ARM feature detection (#10543)

ggml-ci

7 months agoggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
Shupei Fan [Thu, 28 Nov 2024 12:52:03 +0000 (20:52 +0800)]
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)

* ggml-cpu: support IQ4_NL_4_4 by runtime repack

* ggml-cpu: add __ARM_FEATURE_DOTPROD guard

7 months agokompute : improve backend to pass test_backend_ops (#10542)
Sergio López [Thu, 28 Nov 2024 11:51:38 +0000 (12:51 +0100)]
kompute : improve backend to pass test_backend_ops (#10542)

* kompute: op_unary: reject unsupported parameters

Signed-off-by: Sergio Lopez <redacted>
* kompute: softmax: implement ALiBi support

Signed-off-by: Sergio Lopez <redacted>
* kompute: rope: implement neox and phi3 support

Signed-off-by: Sergio Lopez <redacted>
* kompute: op_mul_mat_q4_k permutted support

Signed-off-by: Sergio Lopez <redacted>
* kompute: op_mul_mat_[q4_0|q4_1|q8_0] permutted support

Signed-off-by: Sergio Lopez <redacted>
* kompute: op_mul_mat_f16 permutted support

Signed-off-by: Sergio Lopez <redacted>
* kompute: op_mul_mat_q6_k permutted support

Signed-off-by: Sergio Lopez <redacted>
---------

Signed-off-by: Sergio Lopez <redacted>
7 months agoCANN: Update cann.md to display correctly in CLion (#10538)
Ruixin Huang [Thu, 28 Nov 2024 07:27:11 +0000 (15:27 +0800)]
CANN: Update cann.md to display correctly in CLion (#10538)

7 months agoCANN: Fix SOC_TYPE compile bug (#10519)
leo-pony [Thu, 28 Nov 2024 07:25:24 +0000 (15:25 +0800)]
CANN: Fix SOC_TYPE compile bug (#10519)

* CANN: Fix the bug build fail on Ascend310P under two cases:
1) Manual specify SOC_TYPE
2) Under some unusual compile environment

* Update the cann backend News content: Support F16 and F32 data type model for Ascend 310P NPU.

* fix CANN  compile fail bug: the assert in ascend kernel function doesn't supportted on some CANN version

7 months agoCANN: ROPE operator optimization (#10540)
Chenguang Li [Thu, 28 Nov 2024 06:24:46 +0000 (14:24 +0800)]
CANN: ROPE operator optimization (#10540)

* [cann] ROPE operator optimization

Co-authored-by: noemotiovon <redacted>
7 months agocommon : fix duplicated file name with hf_repo and hf_file (#10550)
Xuan Son Nguyen [Wed, 27 Nov 2024 21:30:52 +0000 (22:30 +0100)]
common : fix duplicated file name with hf_repo and hf_file (#10550)

7 months agoAdd some minimal optimizations for CDNA (#10498)
uvos [Wed, 27 Nov 2024 16:10:08 +0000 (17:10 +0100)]
Add some minimal optimizations for CDNA (#10498)

* Add some minimal optimizations for CDNA

* ggml_cuda: set launch bounds also for GCN as it helps there too

7 months agoci : faster CUDA toolkit installation method and use ccache (#10537)
Diego Devesa [Wed, 27 Nov 2024 10:03:25 +0000 (11:03 +0100)]
ci : faster CUDA toolkit installation method and use ccache (#10537)

* ci : faster CUDA toolkit installation method and use ccache

* remove fetch-depth

* only pack CUDA runtime on master

7 months agometal : fix group_norm support condition (#0)
Georgi Gerganov [Wed, 27 Nov 2024 09:22:14 +0000 (11:22 +0200)]
metal : fix group_norm support condition (#0)

7 months agosync : ggml
Georgi Gerganov [Wed, 27 Nov 2024 09:10:42 +0000 (11:10 +0200)]
sync : ggml

7 months agoDo not include arm_neon.h when compiling CUDA code (ggml/1028)
Frankie Robertson [Tue, 26 Nov 2024 13:50:26 +0000 (15:50 +0200)]
Do not include arm_neon.h when compiling CUDA code (ggml/1028)

7 months agovulkan: define all quant data structures in types.comp (#10440)
Jeff Bolz [Wed, 27 Nov 2024 07:32:54 +0000 (01:32 -0600)]
vulkan: define all quant data structures in types.comp (#10440)

7 months agovulkan: Handle GPUs with less shared memory (#10468)
Jeff Bolz [Wed, 27 Nov 2024 07:30:27 +0000 (01:30 -0600)]
vulkan: Handle GPUs with less shared memory (#10468)

There have been reports of failure to compile on systems with <= 32KB
of shared memory (e.g. #10037). This change makes the large tile size
fall back to a smaller size if necessary, and makes mul_mat_id fall
back to CPU if there's only 16KB of shared memory.

7 months agovulkan: further optimize q5_k mul_mat_vec (#10479)
Jeff Bolz [Wed, 27 Nov 2024 07:21:59 +0000 (01:21 -0600)]
vulkan: further optimize q5_k mul_mat_vec (#10479)

7 months agovulkan: skip integer div/mod in get_offsets for batch_idx==0 (#10506)
Jeff Bolz [Wed, 27 Nov 2024 07:08:54 +0000 (01:08 -0600)]
vulkan: skip integer div/mod in get_offsets for batch_idx==0 (#10506)

7 months agovulkan: optimize Q2_K and Q3_K mul_mat_vec (#10459)
Jeff Bolz [Wed, 27 Nov 2024 07:00:50 +0000 (01:00 -0600)]
vulkan: optimize Q2_K and Q3_K mul_mat_vec (#10459)

7 months agoci : fix cuda releases (#10532)
Diego Devesa [Tue, 26 Nov 2024 21:12:10 +0000 (22:12 +0100)]
ci : fix cuda releases (#10532)

7 months agoAdd OLMo 2 model in docs (#10530)
Shane A [Tue, 26 Nov 2024 20:55:29 +0000 (12:55 -0800)]
Add OLMo 2 model in docs (#10530)

* Add link to OLMo 2 model in docs

* Change link to landing page

7 months agoci : remove nix workflows (#10526)
Diego Devesa [Tue, 26 Nov 2024 20:13:54 +0000 (21:13 +0100)]
ci : remove nix workflows (#10526)

7 months agollama : disable warnings for 3rd party sha1 dependency (#10527)
Diego Devesa [Tue, 26 Nov 2024 20:01:47 +0000 (21:01 +0100)]
llama : disable warnings for 3rd party sha1 dependency (#10527)

7 months agoFix HIP flag inconsistency & build docs (#10524)
Tristan Druyen [Tue, 26 Nov 2024 18:27:28 +0000 (19:27 +0100)]
Fix HIP flag inconsistency & build docs (#10524)

* Fix inconsistency of HIP flags in cmake & make

* Fix docs regarding GGML_HIP

7 months agomtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
R0CKSTAR [Tue, 26 Nov 2024 16:00:41 +0000 (00:00 +0800)]
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)

Signed-off-by: Xiaodong Ye <redacted>
7 months agovulkan: fix group_norm (#10496)
Jeff Bolz [Tue, 26 Nov 2024 15:45:05 +0000 (09:45 -0600)]
vulkan: fix group_norm (#10496)

Fix bad calculation of the end of the range. Add a backend test that
covers the bad case (taken from stable diffusion).

Fixes https://github.com/leejet/stable-diffusion.cpp/issues/439.

7 months agoserver : replace behave with pytest (#10416)
Xuan Son Nguyen [Tue, 26 Nov 2024 15:20:18 +0000 (16:20 +0100)]
server : replace behave with pytest (#10416)

* server : replace behave with pytest

* fix test on windows

* misc

* add more tests

* more tests

* styling

* log less, fix embd test

* added all sequential tests

* fix coding style

* fix save slot test

* add parallel completion test

* fix parallel test

* remove feature files

* update test docs

* no cache_prompt for some tests

* add test_cache_vs_nocache_prompt

7 months agorestore the condistion to build & update pacakge when merge (#10507)
Neo Zhang Jianyu [Tue, 26 Nov 2024 13:43:47 +0000 (21:43 +0800)]
restore the condistion to build & update pacakge when merge (#10507)

Co-authored-by: arthw <redacted>
7 months agocmake : enable warnings in llama (#10474)
Georgi Gerganov [Tue, 26 Nov 2024 12:18:08 +0000 (14:18 +0200)]
cmake : enable warnings in llama (#10474)

* cmake : enable warnings in llama

ggml-ci

* cmake : add llama_get_flags and respect LLAMA_FATAL_WARNINGS

* cmake : get_flags -> ggml_get_flags

* speculative-simple : fix warnings

* cmake : reuse ggml_get_flags

ggml-ci

* speculative-simple : fix compile warning

ggml-ci

7 months agoci : publish the docker images created during scheduled runs (#10515)
Diego Devesa [Tue, 26 Nov 2024 12:05:20 +0000 (13:05 +0100)]
ci : publish the docker images created during scheduled runs (#10515)

7 months agoci : add ubuntu cuda build, build with one arch on windows (#10456)
Diego Devesa [Tue, 26 Nov 2024 12:05:07 +0000 (13:05 +0100)]
ci : add ubuntu cuda build, build with one arch on windows (#10456)

7 months agoggml-cpu: cmake add arm64 cpu feature check for macos (#10487)
Charles Xu [Tue, 26 Nov 2024 11:37:05 +0000 (12:37 +0100)]
ggml-cpu: cmake add arm64 cpu feature check for macos (#10487)

* ggml-cpu: cmake add arm64 cpu feature check for macos

* use vmmlaq_s32 for compile option i8mm check

7 months agoserver : fix parallel speculative decoding (#10513)
Georgi Gerganov [Tue, 26 Nov 2024 11:36:40 +0000 (13:36 +0200)]
server : fix parallel speculative decoding (#10513)

ggml-ci

7 months agospeculative : simplify the implementation (#10504)
Georgi Gerganov [Tue, 26 Nov 2024 10:29:38 +0000 (12:29 +0200)]
speculative : simplify the implementation (#10504)

ggml-ci

7 months agoCANN: Improve the Inferencing Performance for Ascend NPU Device (#10454)
Shanshan Shen [Tue, 26 Nov 2024 10:08:37 +0000 (18:08 +0800)]
CANN: Improve the Inferencing Performance for Ascend NPU Device (#10454)

* improve inferencing performance for ascend npu.

Co-authored-by: Frank Mai <redacted>
* some modification after review

* some modifications after review

* restore some modifications

* restore some modifications

---------

Co-authored-by: shanshan shen <redacted>
Co-authored-by: Frank Mai <redacted>
7 months agoCANN: RoPE and CANCAT operator optimization (#10488)
Chenguang Li [Tue, 26 Nov 2024 09:31:05 +0000 (17:31 +0800)]
CANN: RoPE and CANCAT operator optimization (#10488)

Co-authored-by: noemotiovon <redacted>
7 months agovulkan: Fix a vulkan-shaders-gen arugment parsing error (#10484)
Junil Kim [Tue, 26 Nov 2024 01:47:20 +0000 (10:47 +0900)]
vulkan: Fix a vulkan-shaders-gen arugment parsing error (#10484)

The vulkan-shaders-gen was not parsing the --no-clean argument correctly.
Because the previous code was parsing the arguments which have a value only
and the --no-clean argument does not have a value, it was not being parsed
correctly. This commit can now correctly parse arguments that don't have values.

7 months agoIntroduce llama-run (#10291)
Eric Curtin [Mon, 25 Nov 2024 21:56:24 +0000 (16:56 -0500)]
Introduce llama-run (#10291)

It's like simple-chat but it uses smart pointers to avoid manual
memory cleanups. Less memory leaks in the code now. Avoid printing
multiple dots. Split code into smaller functions. Uses no exception
handling.

Signed-off-by: Eric Curtin <redacted>
7 months agoci : build docker images only once daily (#10503)
Diego Devesa [Mon, 25 Nov 2024 21:05:39 +0000 (22:05 +0100)]
ci : build docker images only once daily (#10503)

7 months agoserver : add more information about error (#10455)
Georgi Gerganov [Mon, 25 Nov 2024 20:28:27 +0000 (22:28 +0200)]
server : add more information about error (#10455)

7 months agoserver : enable cache_prompt by default (#10501)
Georgi Gerganov [Mon, 25 Nov 2024 19:50:07 +0000 (21:50 +0200)]
server : enable cache_prompt by default (#10501)

ggml-ci

7 months agometal : enable mat-vec kernels for bs <= 4 (#10491)
Georgi Gerganov [Mon, 25 Nov 2024 19:49:31 +0000 (21:49 +0200)]
metal : enable mat-vec kernels for bs <= 4 (#10491)

7 months agoRename Olmo1124 to Olmo2 (#10500)
Shane A [Mon, 25 Nov 2024 18:36:09 +0000 (10:36 -0800)]
Rename Olmo1124 to Olmo2 (#10500)

7 months agollama : accept a list of devices to use to offload a model (#10497)
Diego Devesa [Mon, 25 Nov 2024 18:30:06 +0000 (19:30 +0100)]
llama : accept a list of devices to use to offload a model (#10497)

* llama : accept a list of devices to use to offload a model

* accept `--dev none` to completely disable offloading

* fix dev list with dl backends

* rename env parameter to LLAMA_ARG_DEVICE for consistency

7 months agoGithub: update issue templates [no ci] (#10489)
Johannes Gäßler [Mon, 25 Nov 2024 18:18:37 +0000 (19:18 +0100)]
Github: update issue templates [no ci] (#10489)

7 months agoAdd download chat feature to server chat (#10481)
brucepro [Mon, 25 Nov 2024 16:11:55 +0000 (08:11 -0800)]
Add download chat feature to server chat (#10481)

* Add download chat feature to server chat

Add a download feature next to the delete chat feature in the server vue chat interface.

* code style

---------

Co-authored-by: Xuan Son Nguyen <redacted>
7 months agoserver : add speculative decoding support (#10455)
Georgi Gerganov [Mon, 25 Nov 2024 14:31:38 +0000 (16:31 +0200)]
server : add speculative decoding support (#10455)

* server : add speculative decoding support

ggml-ci

* server : add helper function slot.can_speculate()

ggml-ci

7 months agoggml : add support for dynamic loading of backends (#10469)
Diego Devesa [Mon, 25 Nov 2024 14:13:39 +0000 (15:13 +0100)]
ggml : add support for dynamic loading of backends (#10469)

* ggml : add support for dynamic loading of backends

---------

Co-authored-by: Georgi Gerganov <redacted>
7 months agotests : fix compile warning
Georgi Gerganov [Mon, 25 Nov 2024 13:17:32 +0000 (15:17 +0200)]
tests : fix compile warning

7 months agometal : minor code formatting
Georgi Gerganov [Mon, 25 Nov 2024 13:08:04 +0000 (15:08 +0200)]
metal : minor code formatting

7 months ago[SYCL] Fix building Win package for oneAPI 2025.0 update (#10483)
Neo Zhang Jianyu [Mon, 25 Nov 2024 09:31:10 +0000 (17:31 +0800)]
[SYCL] Fix building Win package for oneAPI 2025.0 update (#10483)

* fix build package for 2025.0

* debug

* debug

* fix

* rm debug

---------

Co-authored-by: arthw <redacted>
7 months agospeculative : refactor and add a simpler example (#10362)
Georgi Gerganov [Mon, 25 Nov 2024 07:58:41 +0000 (09:58 +0200)]
speculative : refactor and add a simpler example (#10362)

* speculative : refactor and add a simpler example

ggml-ci

* speculative : clean-up and add comments and TODOs [no ci]

* speculative : manage context in common_speculative

ggml-ci

* speculative : simplify

ggml-ci

* speculative : simplify (cont)

ggml-ci

* speculative : add --draft-min CLI arg

* speculative : minor fixup

* make : build fixes

* speculative : do not redraft previous drafts

ggml-ci

* speculative : fix the draft sampling

ggml-ci

* speculative : fix compile warning

* common : refactor args

ggml-ci

* common : change defaults [no ci]

* common : final touches

ggml-ci

7 months agoflake.lock: Update (#10470)
Georgi Gerganov [Sun, 24 Nov 2024 16:03:25 +0000 (18:03 +0200)]
flake.lock: Update (#10470)

Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/5e4fbfb6b3de1aa2872b76d49fafc942626e2add?narHash=sha256-OZiZ3m8SCMfh3B6bfGC/Bm4x3qc1m2SVEAlkV6iY7Yg%3D' (2024-11-15)
  → 'github:NixOS/nixpkgs/23e89b7da85c3640bbc2173fe04f4bd114342367?narHash=sha256-y/MEyuJ5oBWrWAic/14LaIr/u5E0wRVzyYsouYY3W6w%3D' (2024-11-19)

Co-authored-by: github-actions[bot] <redacted>
7 months agollama : fix op mul check with command-r-plus (#10476)
Diego Devesa [Sun, 24 Nov 2024 15:10:26 +0000 (16:10 +0100)]
llama : fix op mul check with command-r-plus (#10476)

7 months agoconvert : XLMRoberta Type Vocab Size (#10458)
Gabe Goodhart [Sun, 24 Nov 2024 09:02:34 +0000 (02:02 -0700)]
convert : XLMRoberta Type Vocab Size (#10458)

This matches the key in common bert-based embedding models and may have a
value other than 1 in it.

Branch: XLMRobertaTypeVocabSize

Signed-off-by: Gabe Goodhart <redacted>
7 months agofix gguf-py: Conversion error when multiple licenses are configured (#9807)
momonga [Sun, 24 Nov 2024 00:09:22 +0000 (09:09 +0900)]
fix gguf-py:  Conversion error when multiple licenses are configured (#9807)

* fix general.license list to str

* fix join license list

---------

Co-authored-by: momonga <redacted>
7 months agoggml : do not use ARM features not included in the build (#10457)
Diego Devesa [Sat, 23 Nov 2024 13:41:12 +0000 (14:41 +0100)]
ggml : do not use ARM features not included in the build (#10457)

7 months agoci: Update oneAPI runtime dll packaging (#10428)
蕭澧邦 [Fri, 22 Nov 2024 09:44:08 +0000 (17:44 +0800)]
ci: Update oneAPI runtime dll packaging (#10428)

This is the minimum runtime dll dependencies for oneAPI 2025.0

7 months agoGitHub: ask for more info in issue templates (#10426)
Johannes Gäßler [Fri, 22 Nov 2024 07:32:40 +0000 (08:32 +0100)]
GitHub: ask for more info in issue templates (#10426)

* GitHub: ask for more info in issues [no ci]

* refactor issue templates to be component-specific

* more understandable issue description

* add dropdown for llama.cpp module

7 months agoCANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)
leo-pony [Fri, 22 Nov 2024 06:07:20 +0000 (14:07 +0800)]
CANN: Support Ascend310P to accelerate F32 and F16 Model (#10216)

* CANN Support Ascend310P to accelerate F32 and F16 Model

* Add compile option soc type macro ASCEND_310P to ggml-cann lib

* Remove unused code

* Remove the ascend soc_type hard code compile option in CMakelist.txt

7 months agocuda : optimize argmax (#10441)
Diego Devesa [Thu, 21 Nov 2024 17:18:50 +0000 (18:18 +0100)]
cuda : optimize argmax (#10441)

* cuda : optimize argmax

* remove unused parameter

ggml-ci

* fixup : use full warps

ggml-ci

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <redacted>
* fix ub

* ggml : check ne00 <= INT32_MAX in argmax and argsort

---------

Co-authored-by: Johannes Gäßler <redacted>