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
Georgi Gerganov
9dd7a0390f
llama : add log about loading model tensors ( #11699 )
2025-02-06 13:41:37 +02:00
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
c5d4e07664
Merge commit ' acd38efee3' into concedo_experimental
...
# Conflicts:
# .devops/cpu.Dockerfile
# .devops/vulkan.Dockerfile
# .github/workflows/build.yml
# .github/workflows/docker.yml
# CMakeLists.txt
# README.md
# cmake/llama-config.cmake.in
# examples/simple-cmake-pkg/.gitignore
# ggml/CMakeLists.txt
# ggml/src/CMakeLists.txt
# ggml/src/ggml-hip/CMakeLists.txt
2025-01-28 18:16:44 +08:00
Frank Mai
1d8ee06000
rpc: fix register position ( #11424 )
...
Signed-off-by: thxCode <thxcode0824@gmail.com>
2025-01-26 16:20:34 +01:00
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
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
5329df2bdf
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# .github/workflows/server.yml
# CMakeLists.txt
# cmake/build-info.cmake
# examples/run/CMakeLists.txt
# examples/run/run.cpp
# examples/simple-chat/simple-chat.cpp
# tests/CMakeLists.txt
# tests/test-backend-ops.cpp
# tests/test-sampling.cpp
2025-01-21 00:25:07 +08:00
Georgi Gerganov
ef6dada60c
cont : fix whitespaces ( #11305 )
2025-01-20 09:29:32 +02:00
Kyle Bruene
ae3c1db2f9
llama : re-add LLM_ARCH_PHIMOE ( #11305 )
...
Phi 3.5 MoE was partially removed during a refactor. The code was originally in llama.cpp and should be in llama-model.cpp after the refactor.
2025-01-20 09:21:01 +02:00
Concedo
96407502cd
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# README.md
# examples/llama-bench/llama-bench.cpp
# examples/llama.android/llama/src/main/cpp/llama-android.cpp
# examples/llama.android/llama/src/main/java/android/llama/cpp/LLamaAndroid.kt
# src/llama-vocab.cpp
# tests/test-backend-ops.cpp
2025-01-17 23:13:50 +08:00
Radoslav Gerganov
667d72846c
rpc : early register backend devices ( #11262 )
...
Early register RPC devices and do not propagate RPC specifics in the
llama model structures.
ref: #10609
2025-01-17 10:57:09 +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
b154bd3671
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# README.md
# docs/build.md
# docs/development/HOWTO-add-model.md
# tests/test-backend-ops.cpp
# tests/test-chat-template.cpp
2025-01-10 17:57:38 +08:00
Molly Sophia
ee7136c6d1
llama: add support for QRWKV6 model architecture ( #11001 )
...
llama: add support for QRWKV6 model architecture (#11001 )
* WIP: Add support for RWKV6Qwen2
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* RWKV: Some graph simplification
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* Add support for RWKV6Qwen2 with cpu and cuda GLA
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* RWKV6[QWEN2]: Concat lerp weights together to reduce cpu overhead
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* Fix some typos
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* code format changes
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* Fix wkv test & add gla test
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* Fix cuda warning
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* Update README.md
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* Update ggml/src/ggml-cuda/gla.cu
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Fix fused lerp weights loading with RWKV6
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
* better sanity check skipping for QRWKV6 in llama-quant
thanks @compilade
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: compilade <git@compilade.net>
---------
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: compilade <git@compilade.net>
2025-01-10 09:58:08 +08:00
Pierrick Hymbert
f8feb4b01a
model: Add support for PhiMoE arch ( #11003 )
...
* model: support phimoe
* python linter
* doc: minor
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
* doc: minor
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
* doc: add phimoe as supported model
ggml-ci
---------
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
2025-01-09 11:21:41 +01:00
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
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
Georgi Gerganov
727368c60f
llama : use LLAMA_TOKEN_NULL ( #11062 )
...
ggml-ci
2025-01-06 10:52:15 +02:00
fairydreaming
9394bbd484
llama : Add support for DeepSeek V3 ( #11049 )
...
* convert : extend DEEPSEEK2 model architecture to support DeepseekV3ForCausalLM by adding EXPERT_WEIGHTS_NORM and EXPERT_GATING_FUNC model parameters and FFN_EXP_PROBS_B tensor type
* vocab : add DeepSeek V3 pre-tokenizer regexes
* unicode : handle ACCENT_MARK and SYMBOL categories in regex
* llama : add DeepSeek V3 chat template, handle new model parameters and tensor types
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
2025-01-04 21:06:11 +01:00
DAN™
46be942214
llama : add support for the cohere2 model architecture ( #10900 )
2025-01-04 16:33:31 +02:00
Concedo
b4dc29f425
kobo cheats death again (+1 squashed commits)
...
Squashed commits:
[708e2429] kobo cheats death again
2025-01-04 01:06:41 +08:00
Georgi Gerganov
f66f582927
llama : refactor src/llama.cpp ( #10902 )
...
* llama : scatter llama.cpp into multiple modules (wip)
* llama : control-vector -> adapter
* llama : arch
* llama : mmap
ggml-ci
* ci : remove BUILD_SHARED_LIBS=OFF
ggml-ci
* llama : arch (cont)
ggml-ci
* llama : chat
ggml-ci
* llama : model
ggml-ci
* llama : hparams
ggml-ci
* llama : adapter
ggml-ci
* examples : fix
ggml-ci
* rebase
ggml-ci
* minor
* llama : kv cache
ggml-ci
* llama : impl
ggml-ci
* llama : batch
ggml-ci
* cont
ggml-ci
* llama : context
ggml-ci
* minor
* llama : context (cont)
ggml-ci
* llama : model loader
ggml-ci
* common : update lora
ggml-ci
* llama : quant
ggml-ci
* llama : quant (cont)
ggml-ci
* minor [no ci]
2025-01-03 10:18:53 +02:00
