]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-07-04 ditsukebuild: Export hf-to-gguf as snakecase
2024-07-04 ditsukedoc: Add context for why we add an explicit pytorch...
2024-07-04 ditsukechore: Remove rebase artifacts
2024-07-04 ditsukechore: Fixup requirements and build
2024-07-04 ditsukechore: ignore all __pychache__
2024-07-04 ditsukefix: Update script paths in CI scripts
2024-07-04 ditsukefix: Actually include scripts in build
2024-07-04 ditsukebuild(python): Package scripts with pip-0517 compliance
2024-07-04 fairydreamingInference support for T5 and FLAN-T5 model families...
2024-07-04 Daniel Beveniustests : add _CRT_SECURE_NO_WARNINGS for WIN32 (#8231)
2024-07-04 Daniel Beveniusllama : suppress unref var in Windows MSVC (#8150)
2024-07-04 Georgi Gerganovconvert : fix gemma v1 tokenizer convert (#8248)
2024-07-04 AidanBeltonS[SYCL] Remove unneeded semicolons (#8280)
2024-07-03 DanieleDefine and optimize RDNA1 (#8085)
2024-07-03 slarenppl : fix n_seq_max for perplexity (#8277)
2024-07-03 Xuan Son Nguyenfix phi 3 conversion (#8262)
2024-07-03 Juddfix typo (#8267)
2024-07-03 AidanBeltonSDequant improvements rebase (#8255)
2024-07-02 MistApproachfix: add missing short command line argument -mli for...
2024-07-02 Clint HerronAdding step to `clean` target to remove legacy binary...
2024-07-02 Clint HerronRemoves multiple newlines at the end of files that...
2024-07-02 Faisal ZaghloulAdd `JAIS` model(s) (#8118)
2024-07-02 Daniel Beveniusconvert-hf : print output file name when completed...
2024-07-02 slarencuda : update supports_op for matrix multiplication...
2024-07-02 luoyu-intel[SYCL] Fix win build conflict of math library (#8230)
2024-07-02 luoyu-intel[SYCL] Fix the sub group size of Intel (#8106)
2024-07-01 Xuan Son NguyenFix gemma2 tokenizer convert (#8244)
2024-07-01 Johannes GäßlerCUDA: refactor and optimize IQ MMVQ (#8215)
2024-07-01 Mateusz Charytoniukreadme: add Paddler to the list of projects (#8239)
2024-07-01 Xuan Son Nguyengemma2: add sliding window mask (#8227)
2024-07-01 Ronireadme : update tool list (#8209)
2024-07-01 Michael Francisnix : enable curl (#8043)
2024-07-01 Georgi Gerganovnix : remove OpenCL remnants (#8235)
2024-07-01 iacoreDocument BERT support. (#8205)
2024-07-01 zhentaoyu[SYCL] Update SYCL-Rope op and Refactor (#8157)
2024-06-30 Georgi Gerganovflake.lock: Update (#8218)
2024-06-30 Xuan Son NguyenFix new line issue with chat template, disable template...
2024-06-30 Andreillama: Add attention and final logit soft-capping,...
2024-06-28 Xuan Son Nguyenfix code typo in llama-cli (#8198)
2024-06-28 Olivier Chafikjson: attempt to skip slow tests when running under...
2024-06-28 Xuan Son NguyenAdd MiniCPM, Deepseek V2 chat template + clean up ...
2024-06-28 Sigbjørn SkjæretAdd SPM infill support (#8016)
2024-06-28 slarencmake : allow user to override default options (#8178)
2024-06-28 Olivier Chafik`json`: restore default additionalProperties to false...
2024-06-28 pcullitonllama: Add support for Gemma2ForCausalLM (#8156)
2024-06-28 Xuan Son NguyenAdd missing items in makefile (#8177)
2024-06-27 Olivier Chafik`json`: update grammars/README w/ examples & note about...
2024-06-27 loonerinCI: fix release build (Ubuntu+Mac) (#8170)
2024-06-27 slarencmake : fix deprecated option names not working (#8171)
2024-06-27 Xuan Son NguyenAdd chatml fallback for cpp `llama_chat_apply_template...
2024-06-27 Georgi Gerganovflake.lock: Update (#8071)
2024-06-27 jukofyorkControl vector loading fixes (#8137)
2024-06-27 Raj Hammeer... Delete examples/llama.android/llama/CMakeLists.txt...
2024-06-27 Sigbjørn SkjæretAdd Qwen2MoE 57B-A14B model identifier (#8158)
2024-06-27 Johannes GäßlerCUDA: fix MMQ stream-k for --split-mode row (#8167)
2024-06-27 kustaayaAdded support for Viking pre-tokenizer (#8135)
2024-06-27 Sigbjørn Skjæretllama : fix CodeLlama FIM token checks (#8144)
2024-06-27 Raj Hammeer... Fix llama-android.cpp for error - "common/common.h...
2024-06-26 Daniel Beveniusclip : suppress unused variable warnings (#8105)
2024-06-26 Georgi Gerganovscripts : fix filename sync
2024-06-26 slarenci : publish new docker images only when the files...
2024-06-26 slarenggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CU...
2024-06-26 slarenmake : fix missing -O3 (#8143)
2024-06-26 Georgi Gerganovsync : ggml
2024-06-26 Georgi Gerganovauthors : regen
2024-06-26 Georgi Gerganovdevops : remove clblast + LLAMA_CUDA -> GGML_CUDA ...
2024-06-26 Georgi Gerganovreadme : update API notes
2024-06-26 Georgi Gerganovllama : reorganize source code + improve CMake (#8006)
2024-06-26 Isaac McFadyenClarify default MMQ for CUDA and LLAMA_CUDA_FORCE_MMQ...
2024-06-26 Johannes GäßlerCUDA: fix misaligned shared memory read (#8123)
2024-06-26 Eddie-Wangllama : extend llm_build_ffn() to support _scale tensor...
2024-06-26 Olivier Chafik`json`: better support for "type" unions (e.g. nullable...
2024-06-26 Olivier Chafik`json`: fix additionalProperties, allow space after...
2024-06-25 jukofyorkfixes #7999 (adds control vectors to all `build_XXX...
2024-06-25 fairydreamingllama : implement Unigram tokenizer needed by T5 and...
2024-06-25 Daniel Beveniusllama : return nullptr from llama_grammar_init (#8093)
2024-06-25 Olivier Chafik`json`: support integer minimum, maximum, exclusiveMini...
2024-06-25 slarendisable docker CI on pull requests (#8110)
2024-06-25 joecryptotooAdd healthchecks to llama-server containers (#8081)
2024-06-25 BrianGguf dump start data offset via --data-offset and some...
2024-06-25 Xuan Son Nguyencvector: better prompt handling, add "mean vector"...
2024-06-25 Xuan Son NguyenAdd chat template support for llama-cli (#8068)
2024-06-25 HanishKVCSimpleChat v3.1: Boolean chat request options in Settin...
2024-06-25 HatsuneMikuUwU33Update control vector help (#8104)
2024-06-25 Meng, Hengyu[SYCL] Re-enabled mul_mat_batched_sycl (#8095)
2024-06-24 Johannes GäßlerCUDA: fix matrix multiplication algorithm choice (...
2024-06-24 Johannes GäßlerCUDA: fix MMQ writeback for int8 tensor cores (#8100)
2024-06-24 Johannes GäßlerCUDA: use MMQ instead of cuBLAS by default (#8075)
2024-06-24 fairydreaminggguf-py : fix tensor groups for encoder-decoder models...
2024-06-24 Johannes GäßlerCUDA: optimize MMQ int8 tensor core performance (#8062)
2024-06-24 Christian Zhou... Option to split during conversion (#6942)
2024-06-24 slarendisable publishing the full-rocm docker image (#8083)
2024-06-24 Yann Folletembedding : more cli arguments (#7458)
2024-06-24 fairydreaminggguf-py, convert-hf : model conversion support for...
2024-06-24 slarenggml : remove ggml_task_type and GGML_PERF (#8017)
2024-06-23 Eddie-Wangllama : add support for BitnetForCausalLM (#7931)
2024-06-23 Aarni Koskelaserver : fix JSON-Scheme typo (#7975)
2024-06-23 Daniel BeveniusFix typo in llama_set_embeddings comment (#8077)
2024-06-23 slarenfix CI failures (#8066)
2024-06-23 0cc4mRefactor Vulkan backend to allow multiple contexts...
next