Concedo
c088355d01
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .gitignore
# CONTRIBUTING.md
# ggml/CMakeLists.txt
# ggml/cmake/ggml-config.cmake.in
# ggml/src/ggml-cann/kernels/dup.cpp
# ggml/src/ggml-cpu/amx/amx.cpp
# tests/test-backend-ops.cpp
2025-03-01 01:14:35 +08:00
Alex Brooks
84d5f4bc19
Update granite vision docs for 3.2 model ( #12105 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2025-02-28 11:31:47 +00:00
Ting Lou
a800ae46da
llava : add struct for FFI bindgen ( #12079 )
...
* add struct for FFI bindgen
* Apply suggestions from code review
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
2025-02-26 15:26:52 +01:00
Concedo
722fc2dbf1
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# Makefile
# README.md
# docs/backend/SYCL.md
# examples/llava/README.md
# examples/llava/clip.cpp
# examples/run/run.cpp
# examples/server/README.md
# examples/sycl/run-llama2.sh
# ggml/CMakeLists.txt
# ggml/src/ggml-cpu/CMakeLists.txt
# ggml/src/ggml-cuda/CMakeLists.txt
# ggml/src/ggml-hip/CMakeLists.txt
# ggml/src/ggml-musa/CMakeLists.txt
# ggml/src/ggml-sycl/CMakeLists.txt
# tests/test-backend-ops.cpp
2025-02-26 18:44:45 +08:00
Alex Brooks
4d1051a40f
Add Doc for Converting Granite Vision -> GGUF ( #12006 )
...
* Add example docs for granite vision
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2025-02-25 10:46:05 +01:00
Alex Brooks
7a2c913e66
llava : Add Granite Vision Support ( #11794 )
...
* Add super wip scripts for multimodal granite gguf
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Add example for converting mmgranite to gguf
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* remove hardcoded path
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Add vision feature layer to gguf params
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Clean up llava surgery and remove name substitution hacks
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Add transformers llava next tensor name mapping
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Make siglip / openclip mutuall exclusive
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Fix projector linear substitution
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Fix linear 2 substitution index
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Increase max flattened gridpoints to 64
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Fix hardcoded concat for multiple feature layers
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Pull vision feature layers out of gguf keys
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* fix num gridpoints and use all layers
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Avoid dropping last image encoder layer in llava models
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Use 10 for max number of patches
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Standardize vision feature layers
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Cleanup logs
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Update comment for vision feature layer init
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Update notes for alternative to legacy llm conversion script
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Fix notes rendering
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Add v prefix to vision feature layer log
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Use current defaults for feature layer
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Use constant for max gridpoints / feat layers, style fixes
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* clarify non-negative feature layers
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Remove CLIP_API from func signature
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* USE MAX_IMAGE_FEATURE_LAYERS const in layer calc
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Clarify feature layers are non negative ints and not uint
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Fix condition for reading feature layers
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* pop last llava layer when feature layers are unset
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Fix unset vision layer 0
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Update examples/llava/clip.cpp
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
* Reenable assertion for out of bounds get_rows
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Use std vector for gridpoints and feature layers
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Caculate max feature layer at load time
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Include base patch for granite vision allocation
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Fix trailing whitespace
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Add max num patches = 10 back for minicpmv
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Use unordered set to store feature layers
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Use max feature layer for postnorm
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
* Apply suggestions from code review
---------
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
2025-02-24 17:09:51 +01:00
Concedo
159c47f0e6
Merge commit ' 335eb04a91' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CONTRIBUTING.md
# Makefile
# docs/build.md
# examples/llama.swiftui/llama.swiftui/UI/ContentView.swift
# examples/run/run.cpp
# ggml/CMakeLists.txt
# ggml/src/ggml-cpu/CMakeLists.txt
# ggml/src/ggml-cuda/CMakeLists.txt
# ggml/src/ggml-musa/CMakeLists.txt
2025-02-24 11:55:14 +08:00
Ting Lou
36c258ee92
llava: build clip image from pixels ( #11999 )
...
* llava: export function `clip_build_img_from_pixels` to build image from pixels decoded by other libraries instead of stb_image.h for better performance
* Apply suggestions from code review
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
2025-02-22 15:28:28 +01:00
Alex Brooks
ee02ad02c5
clip : fix visual encoders with no CLS ( #11982 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2025-02-21 08:11:03 +02:00
Concedo
f144b1f345
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/llama-cpp-cuda.srpm.spec
# .devops/llama-cpp.srpm.spec
# .devops/nix/package.nix
# .devops/rocm.Dockerfile
# .github/ISSUE_TEMPLATE/020-enhancement.yml
# .github/ISSUE_TEMPLATE/030-research.yml
# .github/ISSUE_TEMPLATE/040-refactor.yml
# .github/ISSUE_TEMPLATE/config.yml
# .github/pull_request_template.md
# .github/workflows/bench.yml.disabled
# .github/workflows/build.yml
# .github/workflows/labeler.yml
# CONTRIBUTING.md
# Makefile
# README.md
# SECURITY.md
# ci/README.md
# common/CMakeLists.txt
# docs/android.md
# docs/backend/SYCL.md
# docs/build.md
# docs/cuda-fedora.md
# docs/development/HOWTO-add-model.md
# docs/docker.md
# docs/install.md
# docs/llguidance.md
# examples/cvector-generator/README.md
# examples/imatrix/README.md
# examples/imatrix/imatrix.cpp
# examples/llama.android/llama/src/main/cpp/CMakeLists.txt
# examples/llama.swiftui/README.md
# examples/llama.vim
# examples/lookahead/README.md
# examples/lookup/README.md
# examples/main/README.md
# examples/passkey/README.md
# examples/pydantic_models_to_grammar_examples.py
# examples/retrieval/README.md
# examples/server/CMakeLists.txt
# examples/server/README.md
# examples/simple-cmake-pkg/README.md
# examples/speculative/README.md
# flake.nix
# grammars/README.md
# pyproject.toml
# scripts/check-requirements.sh
2025-02-16 02:08:39 +08:00
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
db6db9dff9
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# .github/workflows/close-issue.yml
# .github/workflows/server.yml
# AUTHORS
# CMakeLists.txt
# Makefile
# README.md
# cmake/llama.pc.in
# common/CMakeLists.txt
# docs/build.md
# examples/batched.swift/Sources/main.swift
# examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
# examples/llava/CMakeLists.txt
# examples/llava/clip.h
# examples/run/run.cpp
# examples/server/README.md
# ggml/CMakeLists.txt
# ggml/src/ggml-cuda/CMakeLists.txt
# ggml/src/ggml-hip/CMakeLists.txt
# ggml/src/ggml-musa/CMakeLists.txt
# scripts/sync-ggml.last
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
# tests/test-grammar-integration.cpp
# tests/test-json-schema-to-grammar.cpp
2025-02-07 00:52:31 +08:00
SAMI
1ec208083c
llava: add quantization for the visual projector LLAVA, Qwen2VL ( #11644 )
...
* Added quantization for visual projector
* Added README
* Fixed the clip quantize implementation in the file
* Fixed the gcc warning regarding minor linting
* Removed trailing whitespace
2025-02-05 10:45:40 +03:00
piDack
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models ( #10573 )
...
* add glm edge chat model
* use config partial_rotary_factor as rope ratio
* support for glm edge model
* vision model support
* remove debug info
* fix format
* llava.cpp trailing whitespace
* remove unused AutoTokenizer
* Update src/llama.cpp for not contain <|end|> or </s>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* add edge template
* fix chat template
* fix confict
* fix confict
* fix ci err
* fix format err
* fix template err
* 9b hf chat support
* format
* format clip.cpp
* fix format
* Apply suggestions from code review
* Apply suggestions from code review
* Update examples/llava/clip.cpp
* fix format
* minor : style
---------
Co-authored-by: liyuhang <yuhang.li@zhipuai.cn>
Co-authored-by: piDack <pcdack@hotmail.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: liyuhang <yuhang.li@aminer.cn>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-02-02 09:48:46 +02:00
Concedo
70f1d8d746
vision can set max res (+1 squashed commits)
...
Squashed commits:
[938fc655] vision can set max res
2025-01-30 00:19:49 +08:00
Concedo
bec231422a
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# CMakeLists.txt
# Makefile
# README.md
# common/CMakeLists.txt
# docs/backend/SYCL.md
# docs/build.md
# docs/docker.md
# examples/export-lora/export-lora.cpp
# examples/main/README.md
# examples/main/main.cpp
# examples/run/README.md
# examples/run/run.cpp
# examples/server/README.md
# examples/simple-chat/simple-chat.cpp
# ggml/CMakeLists.txt
# ggml/src/ggml-hip/CMakeLists.txt
# src/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
2025-01-25 14:16:50 +08:00
tc-mb
3e3357fd77
llava : support Minicpm-omni ( #11289 )
...
* init
* add readme
* update readme
* no use make
* update readme
* update fix code
* fix editorconfig-checker
* no change convert py
* use clip_image_u8_free
2025-01-22 09:35:48 +02:00
Concedo
2a00ee8fa8
broken commit
2025-01-16 21:41:18 +08:00
Georgi Gerganov
afa8a9ec9b
llama : add llama_vocab, functions -> methods, naming ( #11110 )
...
* llama : functions -> methods (#11110 )
* llama : add struct llama_vocab to the API (#11156 )
ggml-ci
* hparams : move vocab params to llama_vocab (#11159 )
ggml-ci
* vocab : more pimpl (#11165 )
ggml-ci
* vocab : minor tokenization optimizations (#11160 )
ggml-ci
Co-authored-by: Diego Devesa <slarengh@gmail.com>
* lora : update API names (#11167 )
ggml-ci
* llama : update API names to use correct prefix (#11174 )
* llama : update API names to use correct prefix
ggml-ci
* cont
ggml-ci
* cont
ggml-ci
* minor [no ci]
* vocab : llama_vocab_add_[be]os -> llama_vocab_get_add_[be]os (#11174 )
ggml-ci
* vocab : llama_vocab_n_vocab -> llama_vocab_n_tokens (#11174 )
ggml-ci
---------
Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-01-12 11:32:42 +02:00
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
dcfa1eca4e
Merge commit ' 017cc5f446' into concedo_experimental
...
# Conflicts:
# .github/ISSUE_TEMPLATE/010-bug-compilation.yml
# .github/ISSUE_TEMPLATE/019-bug-misc.yml
# CODEOWNERS
# examples/batched-bench/batched-bench.cpp
# examples/batched/batched.cpp
# examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
# examples/gritlm/gritlm.cpp
# examples/llama-bench/llama-bench.cpp
# examples/passkey/passkey.cpp
# examples/quantize-stats/quantize-stats.cpp
# examples/run/run.cpp
# examples/simple-chat/simple-chat.cpp
# examples/simple/simple.cpp
# examples/tokenize/tokenize.cpp
# ggml/CMakeLists.txt
# ggml/src/ggml-metal/CMakeLists.txt
# ggml/src/ggml-vulkan/CMakeLists.txt
# scripts/sync-ggml.last
# src/llama.cpp
# tests/test-autorelease.cpp
# tests/test-model-load-cancel.cpp
# tests/test-tokenizer-0.cpp
# tests/test-tokenizer-1-bpe.cpp
# tests/test-tokenizer-1-spm.cpp
2025-01-08 23:15:21 +08:00
Johannes Gäßler
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes ( #11030 )
...
* GGUF: C++ refactor, backend support, misc fixes
remove ggml_tensor.backend
update CODEOWNERS [no ci]
remove gguf_get_data from API
revise GGUF API data types
2025-01-07 18:01:58 +01:00
Georgi Gerganov
47182dd03f
llama : update llama_model API names ( #11063 )
...
* llama : deprecate llama_free_model, add llama_model_free
ggml-ci
* llama : change `llama_load_model_from_file` -> `llama_model_load_from_file`
ggml-ci
2025-01-06 10:55:18 +02:00
Concedo
b7d3274523
temporarily make qwenv2l use clip on cpu for vulkan and macos
2024-12-21 09:15:31 +08:00
Georgi Gerganov
d408bb9268
clip : disable GPU support ( #10896 )
...
ggml-ci
2024-12-19 18:47:15 +02:00
Concedo
fbf1345a66
clip quantize skip problematic layer
2024-12-19 16:25:48 +08:00
Concedo
ee486bad3e
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# README.md
# examples/CMakeLists.txt
# examples/batched/batched.cpp
# examples/gritlm/gritlm.cpp
# examples/llama.android/llama/build.gradle.kts
# examples/main/README.md
# examples/retrieval/retrieval.cpp
# examples/server/CMakeLists.txt
# examples/server/README.md
# ggml/CMakeLists.txt
# ggml/src/ggml-cpu/CMakeLists.txt
# ggml/src/ggml.c
# scripts/compare-commits.sh
# scripts/sync-ggml.last
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
# tests/test-sampling.cpp
2024-12-19 11:57:43 +08:00
Georgi Gerganov
0bf2d10c55
tts : add OuteTTS support ( #10784 )
...
* server : add "tokens" output
ggml-ci
* server : output embeddings for all tokens when pooling = none
ggml-ci
* server : be explicit about the pooling type in the tests
ggml-ci
* server : do not normalize embeddings when there is no pooling
ggml-ci
* llama : add OuteTTS support (wip)
* wip
* extract features
* first conv
* group norm
* resnet conv
* resnet
* attn
* pos net
* layer norm
* convnext
* head
* hann window
* fix n_embd + remove llama.cpp hacks
* compute hann window
* fft
* spectrum processing
* clean-up
* tts : receive input text and generate codes
* clip : fix new conv name
* tts : minor fix
* tts : add header + minor fixes
ggml-ci
* tts : add matchematical constant
ggml-ci
* tts : fix sampling + cut initial noise
* tts : fixes
* tts : update default samplers
ggml-ci
* tts : text pre-processing
* tts : outetts-voc -> wavtokenizer-dec
* tts : remove hardcoded constants
ggml-ci
* tts : fix tensor shapes
* llama : refactor wavtokenizer tensors
ggml-ci
* cont
ggml-ci
* cont [no ci]
* llama : update WavTokenizer to non-causal attn
* llama : handle no-vocab detokenization
* tts : add Python example for OuteTTS (wip)
* tts : extend python example to generate spectrogram
ggml-ci
* server : fix rebase artifacts
* tts : enable "return_tokens" in Python example
ggml-ci
* tts : minor fixes
* common : support HF download for vocoder
2024-12-18 19:27:21 +02:00
Bartowski
4ddd199f6f
llava : Allow locally downloaded models for QwenVL ( #10833 )
...
* Allow locally downloaded models for QwenVL
* Define model_path
* rm trailing space
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
2024-12-15 21:43:25 +01:00
Concedo
f456ed7237
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/nix/package.nix
# .devops/tools.sh
# .github/workflows/build.yml
# Makefile
# README.md
# common/CMakeLists.txt
# common/common.h
# examples/llava/CMakeLists.txt
# examples/run/CMakeLists.txt
# examples/run/README.md
# examples/run/run.cpp
# ggml/CMakeLists.txt
# ggml/src/CMakeLists.txt
# ggml/src/ggml-kompute/ggml-kompute.cpp
# tests/test-backend-ops.cpp
# tests/test-rope.cpp
2024-12-15 15:30:10 +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
4c4ce5e808
rewritten checkpoint 1 - before coopmat
2024-12-13 16:55:23 +08:00
piDack
01e6d9bb71
clip : add sycl support ( #10574 )
...
Co-authored-by: piDack <pcdack@hotmail.co>
2024-12-04 01:26:37 +01:00
Concedo
697ca70115
temp checkpoint
2024-11-30 12:13:20 +08:00
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
Ting Lou
678d7994f4
llava: return false instead of exit ( #10546 )
2024-11-29 01:09:46 +01:00
Concedo
83350ec314
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/ISSUE_TEMPLATE/020-enhancement.yml
# .github/ISSUE_TEMPLATE/030-research.yml
# .github/ISSUE_TEMPLATE/040-refactor.yml
# .github/workflows/build.yml
# Makefile
# common/CMakeLists.txt
# examples/CMakeLists.txt
# examples/infill/infill.cpp
# examples/lookahead/lookahead.cpp
# examples/lookup/lookup-stats.cpp
# examples/lookup/lookup.cpp
# examples/parallel/parallel.cpp
# examples/retrieval/retrieval.cpp
# examples/save-load-state/save-load-state.cpp
# examples/speculative/speculative.cpp
# flake.lock
# ggml/src/ggml-cann/CMakeLists.txt
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/kernels/CMakeLists.txt
# ggml/src/ggml-cann/kernels/dup.cpp
# ggml/src/ggml-cann/kernels/get_row_f16.cpp
# ggml/src/ggml-cann/kernels/get_row_f32.cpp
# ggml/src/ggml-cann/kernels/get_row_q4_0.cpp
# tests/test-arg-parser.cpp
# tests/test-backend-ops.cpp
2024-11-25 16:26:08 +08:00
Georgi Gerganov
d9d54e498d
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
2024-11-25 09:58:41 +02:00
Concedo
bb13925f39
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# CMakePresets.json
# Makefile
# Package.swift
# ci/run.sh
# common/CMakeLists.txt
# examples/CMakeLists.txt
# flake.lock
# ggml/src/CMakeLists.txt
# ggml/src/ggml-backend.cpp
# ggml/src/ggml.c
# pocs/vdot/q8dot.cpp
# pocs/vdot/vdot.cpp
# tests/test-backend-ops.cpp
# tests/test-grad0.cpp
# tests/test-quantize-fns.cpp
# tests/test-quantize-perf.cpp
# tests/test-rope.cpp
2024-11-04 16:54:53 +08:00
Diego Devesa
9f40989351
ggml : move CPU backend to a separate file ( #10144 )
2024-11-03 19:34:08 +01:00
Concedo
94a5a27b85
Alone in the darkness
...
They're coming for you
I know they will try to catch me too
Alone in the darkness
They're calling for you
There's nowhere to run for cover
2024-10-24 22:29:20 +08:00
Xuan Son Nguyen
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch ( #9745 )
...
* refactor llama_batch_get_one
* adapt all examples
* fix simple.cpp
* fix llama_bench
* fix
* fix context shifting
* free batch before return
* use common_batch_add, reuse llama_batch in loop
* null terminated seq_id list
* fix save-load-state example
* fix perplexity
* correct token pos in llama_batch_allocr
2024-10-18 23:18:01 +02:00
Concedo
a9dbcdd3ec
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# README.md
# docs/build.md
# examples/infill/infill.cpp
# examples/main/README.md
# examples/server/README.md
# flake.lock
# scripts/sync-ggml.last
# src/llama.cpp
# tests/test-json-schema-to-grammar.cpp
# tests/test-sampling.cpp
2024-10-17 16:36:02 +08:00
Daniel Bevenius
dbf18e4de9
llava : fix typo in error message [no ci] ( #9884 )
2024-10-16 20:24:05 +03:00
Concedo
e692a79aab
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/docker.yml
# CMakeLists.txt
# CONTRIBUTING.md
# docs/android.md
# docs/docker.md
# examples/embedding/embedding.cpp
# examples/imatrix/imatrix.cpp
# examples/infill/infill.cpp
# examples/llama-bench/llama-bench.cpp
# examples/main/README.md
# examples/parallel/parallel.cpp
# examples/perplexity/perplexity.cpp
# examples/quantize-stats/quantize-stats.cpp
# examples/save-load-state/save-load-state.cpp
# examples/server/README.md
# examples/simple/CMakeLists.txt
# examples/speculative/speculative.cpp
# flake.lock
# ggml/src/CMakeLists.txt
# ggml/src/ggml-blas.cpp
# pocs/vdot/q8dot.cpp
# pocs/vdot/vdot.cpp
# scripts/debug-test.sh
# scripts/sync-ggml.last
# src/llama.cpp
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
# tests/test-quantize-fns.cpp
# tests/test-quantize-perf.cpp
# tests/test-tokenizer-0.cpp
# tests/test-tokenizer-1-bpe.cpp
# tests/test-tokenizer-1-spm.cpp
2024-10-11 11:59:59 +08:00
Diego Devesa
7eee341bee
common : use common_ prefix for common library functions ( #9805 )
...
* common : use common_ prefix for common library functions
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-10-10 22:57:42 +02:00
Concedo
ce7f9c9a2c
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/full-rocm.Dockerfile
# .devops/llama-cli-rocm.Dockerfile
# .devops/llama-server-rocm.Dockerfile
# .github/workflows/build.yml
# .github/workflows/python-type-check.yml
# CMakeLists.txt
# CONTRIBUTING.md
# README.md
# ci/run.sh
# examples/embedding/embedding.cpp
# examples/server/README.md
# flake.lock
# ggml/include/ggml.h
# ggml/src/ggml.c
# requirements/requirements-convert_legacy_llama.txt
# scripts/sync-ggml.last
# src/llama-vocab.cpp
# src/llama.cpp
# tests/test-backend-ops.cpp
# tests/test-grad0.cpp
# tests/test-tokenizer-0.cpp
2024-10-02 01:00:57 +08:00
Georgi Gerganov
cad341d889
metal : reduce command encoding overhead ( #9698 )
...
* metal : reduce command encoding overhead
ggml-ci
* metal : add comments
2024-10-01 16:00:25 +03:00
compilade
511636df0c
ci : reduce severity of unused Pyright ignore comments ( #9697 )
2024-09-30 14:13:16 -04:00
Concedo
29625c3d2e
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# .github/workflows/server.yml
# CMakeLists.txt
# Makefile
# README.md
# ci/run.sh
# common/CMakeLists.txt
# common/common.cpp
# docs/backend/SYCL.md
# examples/embedding/embedding.cpp
# examples/imatrix/imatrix.cpp
# examples/infill/infill.cpp
# examples/llama-bench/llama-bench.cpp
# examples/main/README.md
# examples/parallel/parallel.cpp
# examples/perplexity/perplexity.cpp
# examples/server/CMakeLists.txt
# examples/server/README.md
# examples/server/bench/README.md
# examples/server/tests/README.md
# examples/speculative/speculative.cpp
# flake.lock
# ggml/CMakeLists.txt
# ggml/src/CMakeLists.txt
# grammars/README.md
# scripts/compare-commits.sh
# scripts/compare-llama-bench.py
# tests/CMakeLists.txt
2024-09-19 14:53:57 +08:00
