]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-04-30 Kevin Gibbonsswitch to using localizedDescription (#7010)
2024-04-30 Georgi Gerganovmetal : remove deprecated error code (#7008)
2024-04-30 Kevin Gibbonsmetal : log more info on error (#6987)
2024-04-30 Georgi Gerganovggml : add Flash Attention (#5021)
2024-04-30 Georgi Gerganovconvert : use utf8 encoding (#7000)
2024-04-29 Olivier ChafikImprove usability of --model-url & related flags (...
2024-04-29 Clint HerronExtending grammar integration tests (#6644)
2024-04-29 Daniel Beveniusmain : fix typo in comment in main.cpp (#6985)
2024-04-29 Olivier Chafikbuild(cmake): simplify instructions (`cmake -B build...
2024-04-29 Georgi Gerganovci : tmp disable gguf-split (#6983)
2024-04-29 Georgi Gerganovggml : fix __MSC_VER -> _MSC_VER (#6977)
2024-04-29 cpumaxxllava-cli : multiple images (#6969)
2024-04-29 Georgi Gerganovreadme : update hot topics
2024-04-29 Georgi Gerganovllama : fix BPE pre-tokenization (#6920)
2024-04-29 David Renshawsampling : use std::random_device{}() for default rando...
2024-04-29 Christian Zhou... convert : fix conversion of some BERT embedding models...
2024-04-29 Przemysław... make : change GNU make default CXX from g++ to c++...
2024-04-29 Przemysław... ci : add building in MSYS2 environments (Windows) ...
2024-04-29 Johannes Gäßlerllama : fix typo LAMMAFILE -> LLAMAFILE (#6974)
2024-04-28 DAN™Fix more int overflow during quant (PPL/CUDA). (#6563)
2024-04-28 Xuan Son Nguyengguf : enforce that tensor names are unique (#6905)
2024-04-28 Neo Zhangadd device version in device list (#6959)
2024-04-28 github-actions... flake.lock: Update
2024-04-27 mgroeber9110Replace "alternative" boolean operator in conditional...
2024-04-27 Pierrick Hymbertci: server: tests python env on github container ubuntu...
2024-04-26 agray3Reset schedule earlier to allow overlap with ggml graph...
2024-04-26 Pierrick Hymbertquantize: add imatrix and dataset metadata in GGUF...
2024-04-26 slarenadd basic tensor data validation function (#6884)
2024-04-26 slarengguf : fix mismatch between alloc and free functions...
2024-04-26 Justine Tunneyllamafile : use 64-bit integers in sgemm (#6928)
2024-04-26 Pierrick Hymbertci: server: fix python installation (#6925)
2024-04-26 Pierrick Hymbertserver: stop generation at `n_ctx_train` if `n_predict...
2024-04-26 Pierrick Hymbertci: server: fix python installation (#6922)
2024-04-26 Georgi GerganovMerge pull request from GHSA-p5mv-gjc5-mwqv
2024-04-26 Pierrick Hymbertci: server: fix python installation (#6918)
2024-04-26 Pierrick Hymbertci: fix concurrency for pull_request_target (#6917)
2024-04-26 Pierrick Hymbertbench: server add stop word for PHI-2 (#6916)
2024-04-25 vikllava : add support for moondream vision language model...
2024-04-25 Georgi Gerganovcmake : restore LLAMA_LLAMAFILE_DEFAULT
2024-04-25 Georgi Gerganovcmake : remove obsolete ANDROID check
2024-04-25 slarenllama : synchronize before get/set session data (#6911)
2024-04-25 Georgi Gerganovci : tmp disable slow tests
2024-04-25 BarfingLemursreadme : update model list (#6908)
2024-04-25 slarenllama : check that all the tensor data is in the model...
2024-04-25 Georgi Gerganovggml : fix redefinition of vaddvq_f32 for 32-bit ARM...
2024-04-25 Daniel Beveniusclip : rename lerp function to avoid conflict (#6894)
2024-04-25 Georgi Gerganovggml : fix MIN / MAX macros (#6904)
2024-04-25 Georgi Gerganovtests : minor bash stuff (#6902)
2024-04-25 jiezquantize : add '--keep-split' to quantize model into...
2024-04-24 Johannes GäßlerREADME: add graphic for matrix multiplication (#6881)
2024-04-24 Douglas Hanleyllama : add llama_get_pooling_type function (#6862)
2024-04-24 mgroeber9110server : do not apply Markdown formatting in code secti...
2024-04-24 Kyle Mistelecommon : revert showing control tokens by default for...
2024-04-24 Johannes GäßlerServer: fix seed for multiple slots (#6835)
2024-04-24 Georgi Gerganovggml : move 32-bit arm compat in ggml-impl.h (#6865)
2024-04-24 Tristan Druyenllama : add phi 3 chat template (#6857)
2024-04-24 Junyang Linconvert : add support of codeqwen due to tokenizer...
2024-04-24 liuwei-gitllama : add phi3 support (#6852)
2024-04-23 Anas Ahouzi[SYCL] Windows default build instructions without ...
2024-04-22 Justine Tunneyllamafile : improve sgemm.cpp (#6796)
2024-04-22 Dave Airlieggml : fix calloc argument ordering. (#6820)
2024-04-22 Georgi Gerganovllama : fix typo in <|im_end|> token text (#6745)
2024-04-22 Pierrick Hymbertci: fix job are cancelling each other (#6781)
2024-04-22 github-actions... flake.lock: Update
2024-04-21 Olivier Chafik`build`: generate hex dump of server assets during...
2024-04-21 Georgi Gerganovllama : add option to render special/control tokens...
2024-04-21 Georgi Gerganovggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
2024-04-21 Wouterllama : add llama-3 chat template (#6751)
2024-04-21 pmyslgguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
2024-04-21 Jan Boondoc : add link to falcon (#6789)
2024-04-21 Mohammadreza... readme : add Fedora instructions (#6783)
2024-04-21 Justine Tunneyllava : use logger in llava-cli (#6797)
2024-04-21 Pedro Cuencallama : support Llama 3 HF conversion (#6745)
2024-04-20 Jan Boondoc : server tests require llama to be built with curl...
2024-04-20 Georgi Gerganovcommon : try to fix Android CI (#6780)
2024-04-19 loonerinci: add ubuntu latest release and fix missing build...
2024-04-19 Pierrick Hymbertserver: static: upstream upgrade (#6765)
2024-04-19 nopperlImplement the OLMo architecture (#6741)
2024-04-19 Austintrain : add general name (#6752)
2024-04-19 Neo Zhangfix wrong parameter in cmd in readme-sycl.md (#6755)
2024-04-18 slarenggml : group all experts in a single ggml_mul_mat_id...
2024-04-18 Sigbjørn Skjæretconvert : support models with multiple chat templates...
2024-04-18 Ren XuanchengQwen2 : assume tied weights if lm_head/output weights...
2024-04-18 slarenllama : fix compatibility with old 2 expert models...
2024-04-17 Georgi Gerganovllamafile : tmp disable + build sgemm.o when needed...
2024-04-17 Yaroslavreadme : add UI (#6724)
2024-04-16 Zheng.Dengconvert : fix autoawq gemma (#6704)
2024-04-16 Georgi Gerganovllama : make general.name optional (#6709)
2024-04-16 Georgi Gerganovggml : fix llamafile sgemm wdata offsets (#6710)
2024-04-16 Justine Tunneyggml : add llamafile sgemm (#6414)
2024-04-16 Ashishllama : add StableLM2 12B (#6635)
2024-04-16 Shijiellama : add qwen2moe (#6074)
2024-04-16 Daniel Beveniusgritlm : add --outdir option to hf.sh script (#6699)
2024-04-16 Georgi Gerganovperplexity : require positive --ctx-size arg (#6695)
2024-04-16 Daniel Beveniusgguf : add special tokens metadata for FIM/Infill ...
2024-04-15 Olivier Chafik`main`: add --json-schema / -j flag (#6659)
2024-04-15 compiladellama : fix restoring the number of outputs from state...
2024-04-15 Pierrick Hymbertserver : revert "minor layout improvements" (#6684)
2024-04-15 Steven Prichardswift : linux support (#6590)
2024-04-15 Neo Zhang Jianyufix mul_mat_id() for new input, make the ut pass (...
next