Concedo
e1d3c19673
clblast not working correctly
2025-03-30 21:02:30 +08:00
Concedo
61a73347c6
fixed mrope for multiple images in qwen2vl (+1 squashed commits)
...
Squashed commits:
[63e4d91c] fixed mrope for multiple images in qwen2vl (+1 squashed commits)
Squashed commits:
[bb78db1e] wip fixing mrope
2025-03-30 17:23:58 +08:00
Concedo
3992fb79cc
wip adding embeddings support
2025-03-24 18:01:23 +08:00
Concedo
9910f3abe0
remove precompiled vulkan shaders from repo. They will now have to be recreated in vulkan-shaders-gen from scratch at runtime, which is auto handled by the makefile for windows and linux.
2025-03-19 21:51:16 +08:00
Concedo
0cfd8d23cb
handle symlinks (+1 squashed commits)
...
Squashed commits:
[fb8477b9] fixed makefile (+4 squashed commit)
Squashed commit:
[4a245bba] fixed a makefile issue
[d68eba69] alias usehipblas to usecublas
[a9ab0a7c] dynamic rocwmma selection
[fefe17c7] revert rocwmma
2025-03-17 21:03:30 +08:00
Concedo
98eade358a
more rocm include dir
2025-03-15 23:29:00 +08:00
Concedo
2c9ade61fe
test automatic vk shader rebuilding
2025-03-13 19:34:15 +08:00
Concedo
77debb1b1b
gemma3 vision works, but is using more tokens than expected - may need resizing
2025-03-13 00:31:16 +08:00
Concedo
e500968f92
fixed ggml common path in metal build
2025-03-12 10:58:57 +08:00
R0CKSTAR
251364549f
musa: support new arch mp_31 and update doc ( #12296 )
...
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2025-03-10 18:18:25 +01:00
Concedo
7eadd0a1d3
add GGML_HIP_ROCWMMA_FATTN
2025-03-08 17:15:41 +08:00
Concedo
6b7d2349a7
Rewrite history to fix bad vulkan shader commits without increasing repo size
...
added dpe colab (+8 squashed commit)
Squashed commit:
[b8362da4] updated lite
[ed6c037d] move nsigma into the regular sampler stack
[ac5f61c6] relative filepath fixed
[05fe96ab] export template
[ed0a5a3e] nix_example.md: refactor (#1401 )
* nix_example.md: add override example
* nix_example.md: drop graphics example, already basic nixos knowledge
* nix_example.md: format
* nix_example.md: Vulkan is disabled on macOS
Disabled in: 1ccd253acchttps://github.com/LostRuins/koboldcpp/issues/1367
[675c62f7] AutoGuess: Phi 4 (mini) (#1402 )
[4bf56982b8c0df04#1397 )
- place after nsigma and before xtc (+3 squashed commit)
Squashed commit:
[87c52b97ee8906f3e85c0e69#1394 )
* stop counting reps
* fix range-based initializer
* strike that - reverse it
2025-03-05 00:02:20 +08:00
Johannes Gäßler
a28e0d5eb1
CUDA: app option to compile without FlashAttention ( #12025 )
2025-02-22 20:44:34 +01:00
Bodhi
0b3863ff95
MUSA: support ARM64 and enable dp4a .etc ( #11843 )
...
* MUSA: support ARM64 and enable __dp4a .etc
* fix cross entropy loss op for musa
* update
* add cc info log for musa
* add comment for the MUSA .cc calculation block
---------
Co-authored-by: Bodhi Hu <huaishun.hu@mthreads.com>
2025-02-21 09:46:23 +02:00
Olivier Chafik
63e489c025
tool-call: refactor common chat / tool-call api (+ tests / fixes) ( #11900 )
...
* tool-call refactoring: moved common_chat_* to chat.h, common_chat_templates_init return a unique_ptr to opaque type
* addressed clang-tidy lints in [test-]chat.*
* rm minja deps from util & common & move it to common/minja/
* add name & tool_call_id to common_chat_msg
* add common_chat_tool
* added json <-> tools, msgs conversions to chat.h
* fix double bos/eos jinja avoidance hack (was preventing inner bos/eos tokens)
* fix deepseek r1 slow test (no longer <think> opening w/ new template)
* allow empty tools w/ auto + grammar
* fix & test server grammar & json_schema params w/ & w/o --jinja
2025-02-18 18:03:23 +00:00
Georgi Gerganov
68ff663a04
repo : update links to new url ( #11886 )
...
* repo : update links to new url
ggml-ci
* cont : more urls
ggml-ci
2025-02-15 16:40:57 +02:00
Concedo
816d9b7989
edit makefile flags
2025-02-08 22:36:26 +08:00
Concedo
ff9b4041da
fix builds
2025-02-07 11:46:08 +08:00
Johannes Gäßler
864a0b67a6
CUDA: use mma PTX instructions for FlashAttention ( #11583 )
...
* CUDA: use mma PTX instructions for FlashAttention
* __shfl_sync workaround for movmatrix
* add __shfl_sync to HIP
Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-02-02 19:31:09 +01:00
Concedo
f13498df13
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/tools.sh
# .devops/vulkan.Dockerfile
# .github/workflows/build.yml
# .github/workflows/docker.yml
# .github/workflows/server.yml
# Makefile
# README.md
# cmake/llama-config.cmake.in
# common/CMakeLists.txt
# examples/gbnf-validator/gbnf-validator.cpp
# examples/run/run.cpp
# examples/server/README.md
# examples/server/tests/README.md
# ggml/src/CMakeLists.txt
# ggml/src/ggml-hip/CMakeLists.txt
# scripts/sync-ggml.last
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
# tests/test-grammar-integration.cpp
2025-02-01 17:14:59 +08:00
Olivier Chafik
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars ( #9639 )
...
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2025-01-30 19:13:58 +00:00
Concedo
7a5499e77b
added one more backend for clblast noavx2 and clblast failsafe
2025-01-30 22:47:22 +08:00
Concedo
898856e183
cleaned up unused flags from makefile, updated lite
2025-01-30 19:34:55 +08:00
Concedo
2f69432774
makefile indentation fix (+1 squashed commits)
...
Squashed commits:
[f640eb59] makefile indentation fix
2025-01-29 22:18:54 +08:00
Olivier Chafik
6171c9d258
Add Jinja template support ( #11016 )
...
* Copy minja from 58f0ca6dd7https://github.com/google/minja/pull/22 )
* Apply suggestions from code review
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Finish suggested renamings
* Move chat_templates inside server_context + remove mutex
* Update --chat-template-file w/ recent change to --chat-template
* Refactor chat template validation
* Guard against missing eos/bos tokens (null token otherwise throws in llama_vocab::impl::token_get_attr)
* Warn against missing eos / bos tokens when jinja template references them
* rename: common_chat_template[s]
* reinstate assert on chat_templates.template_default
* Update minja to b8437df626https://github.com/google/minja/pull/25
* Update minja from https://github.com/google/minja/pull/27
* rm unused optional header
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-01-21 13:18:51 +00:00
Concedo
b3de1598e7
Fixed some GGUFv1 loading bugs, long overdue cleanup for compiling, integrated TTS
...
tts is functional (+6 squashed commit)
Squashed commit:
[22396311] wip tts
[3a883027] tts not yet working
[0dcfab0e] fix silly bug
[a378d9ef] some long overdue cleanup
[fc5a6fb5] Wip tts
[39f50497] wip TTS integration
2025-01-13 14:23:25 +08:00
Concedo
bd38665e1f
some cleanup before starting on TTS
2025-01-10 22:13:44 +08:00
Concedo
e788b8289a
You'll never take us alive
...
We swore that death will do us part
They'll call our crimes a work of art
2025-01-09 11:27:06 +08:00
Concedo
bb2e739627
fixed simplercflags
2025-01-07 21:34:38 +08:00
Concedo
58791612d2
sse3 mode for noavx2 clblast, fixed metadata, added version command
2025-01-06 21:59:05 +08:00
Concedo
b4dc29f425
kobo cheats death again (+1 squashed commits)
...
Squashed commits:
[708e2429] kobo cheats death again
2025-01-04 01:06:41 +08:00
Concedo
22fd7a0439
fix make tools for linux
2025-01-03 11:39:23 +08:00
Concedo
2a890ec25a
Breaking change: unify the windows and linux build flags.
...
To do a full build on windows you now need LLAMA_PORTABLE=1 LLAMA_VULKAN=1 LLAMA_CLBLAST=1
2024-12-23 22:35:54 +08:00
Concedo
1e07043a6e
clean and rename old clblast files in preparation for merge
2024-12-15 15:29:02 +08:00
HimariO
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE ( #10361 )
...
* Barebone Qwen2VL LLM convertor
* Add Qwen2VL cli entrypoint
* [WIP] add qwen2vl arch
* Verify m-rope output
* Add vl-rope/2d-rope support for qwen2vl ViT
* update qwen2vl cli tool
* update 5D tensor op workaround
* [WIP] qwen2vl vision model
* make batch and clip utils compatible with qwen2vl
* [WIP] create inference workflow, gguf convert script but fix
* correcting vision-rope behavior, add the missing last layer back to ViT
* add arg parser to qwen2vl_surgery
* replace variable size array with vector
* cuda-gdb cmake preset
* add fp32 mrope, vision rope kernel
* add fp16 support for qwen2vl and m-rope
* add `GGML_ROPE_TYPE_MROPE`, `GGML_ROPE_TYPE_VISION`
* fix rope op mode switching, out dated func args
* update `llama_hparams`
* update to keep up stream changes
* resolve linter, test errors
* add makefile entry, update speical image padding token
* add mrope unit test, fix few compiler warnings
* rename `mrope` related function, params
* minor updates on debug util, bug fixs
* add `m-rope` testcase to `test-backend-ops`
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* fix traililng whitespce
* store `llama_hparams.rope_sections` with fixed size array
* update position id tensor size check in GGML_OP_ROPE
* minor updates
* update `ggml_backend_*_supports_op` of unsupported backends
* remote old `rope_section` compare operator
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-12-14 14:43:46 +02:00
Concedo
a63c2c914d
made shaders gen deterministic, update to c++17 (+4 squashed commit)
...
Squashed commit:
[7bb2441b] made shaders gen deterministic
[906e02af] Update c++ from 11 to 17 (#1263 )
* Update c/c++ from 11 to 17
* Update CMakeLists.txt
only bump c++
[7ca430ed] C++17 ver
[b7dfb55d
2024-12-13 23:07:10 +08:00
Concedo
7e1abf3aaf
sync - fix cmake failing to build with c++11, updated glslc.exe to handle coopmat, sync sdtype count, aarch repack flags
2024-12-13 17:08:10 +08:00
Concedo
de64b9198c
merge checkpoint 2 - functional merge without q4_0_4_4 (need regen shaders)
2024-12-13 17:04:19 +08:00
Concedo
4548d893ee
better way to handle termux compatibility (+2 squashed commit)
...
Squashed commit:
[301986f11] better way to handle termux compatibility
[16b03b225] updated lite
2024-12-11 15:05:01 +08:00
Concedo
a11bba5893
cleanup, fix native build for arm (+28 squashed commit)
...
Squashed commit:
[d1f6a4154] bundle library
[947ab84b7] undo
[0f9aba8d8] test
[e9ac93873] test
[920438202] test
[1c6d98804acf8ec8940acf8ec8946a99372335a263a5bdddfd82bca0b30e45dac3bfece552a4b37fe080a1fcaeaf80a1fcaeae2aa7d944264d80200f5b1231731ffacc48463c0be926510e0377e4ac199b201bc987ba27697252b1f87087b28e9dfe2cefb411192db25b5301e558038cddc
2024-12-10 19:42:23 +08:00
Djip007
19d8762ab6
ggml : refactor online repacking ( #10446 )
...
* rename ggml-cpu-aarch64.c to .cpp
* reformat extra cpu backend.
- clean Q4_0_N_M and IQ4_0_N_M
- remove from "file" tensor type
- allow only with dynamic repack
- extract cpu extra bufts and convert to C++
- hbm
- "aarch64"
- more generic use of extra buffer
- generalise extra_supports_op
- new API for "cpu-accel":
- amx
- aarch64
* clang-format
* Clean Q4_0_N_M ref
Enable restrict on C++
* add op GGML_OP_MUL_MAT_ID for Q4_0_N_M with runtime repack
* added/corrected control on tensor size for Q4 repacking.
* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* add debug logs on repacks.
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-12-07 14:37:50 +02:00
Concedo
ece96e19bf
clean up makefile
2024-12-05 23:58:23 +08:00
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
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
Wang Qin
43957ef203
build: update Makefile comments for C++ version change ( #10598 )
2024-12-01 04:19:44 +01:00
Diego Devesa
7cc2d2c889
ggml : move AMX to the CPU backend ( #10570 )
...
* ggml : move AMX to the CPU backend
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-11-29 21:54:58 +01:00
Tristan Druyen
be0e350c8b
Fix HIP flag inconsistency & build docs ( #10524 )
...
* Fix inconsistency of HIP flags in cmake & make
* Fix docs regarding GGML_HIP
2024-11-26 19:27:28 +01:00
R0CKSTAR
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make ( #10516 )
...
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2024-11-26 17:00:41 +01:00
Concedo
b9e99c69e8
fixed build
2024-11-26 22:06:55 +08:00
Eric Curtin
0cc63754b8
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 <ecurtin@redhat.com>
2024-11-25 22:56:24 +01:00
