]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2023-10-22 Georgi Gerganovbatched : add len CLI argument
2023-10-20 shibe2CLBlast: Add outer loops over src0 for broadcasting...
2023-10-20 Georgi Gerganovsampling : refactor init to use llama_sampling_params...
2023-10-20 Qin Yue Chengguf : support big endian platform (#3552)
2023-10-20 Georgi Gerganovserver : fix uninitialized sampling context (close...
2023-10-20 Herman Semenovggml : fix rope + llama minor optimizations (#3560)
2023-10-20 cebtenzzreconvert : restore compat with old Falcon models (#3680)
2023-10-19 M. Yusuf Sarıgözmultimodal : add BakLLaVA conversion support (#3682)
2023-10-19 M. Yusuf Sarıgözllava : avoid segfault in case of non-existent mmproj...
2023-10-18 Georgi Gerganovreadme : update hot topics
2023-10-18 Georgi Gerganovspeculative : bug fixes
2023-10-18 Georgi Gerganovspeculative : add tree-based sampling example (#3624)
2023-10-18 Jhen-Jie Hongmetal : implement q5_0 and q5_1 kernels (#3648)
2023-10-18 shibe2opencl : fix element-wise multiplication (#3656)
2023-10-17 slarenfix embeddings when using CUDA (#3657)
2023-10-17 Georgi Gerganovllama : avoid fprintf in favor of LLAMA_LOG (#3538)
2023-10-17 BarfingLemursreadme : update hot-topics & models, detail windows...
2023-10-17 shibe2CLBlast: Fix temporary buffer size for f16 conversion...
2023-10-17 slarentrain-text-from-scratch : fix assert failure in ggml...
2023-10-17 Georgi Gerganoveditorconfig : remove trailing spaces
2023-10-17 coezbekserver : documentation of JSON return value of /complet...
2023-10-17 Georgi Gerganovsave-load-state : fix example + add ci test (#3655)
2023-10-17 ldwangreadme : add Aquila2 links (#3610)
2023-10-17 staviqtokenizer : special token handling (#3538)
2023-10-17 Georgi Gerganovk-quants : fix quantization ranges (#3646)
2023-10-16 Georgi Gerganovllava : fix tokenization to not add bos between image...
2023-10-15 cebtenzzreMPT : support GQA for replit-code-v1.5 (#3627)
2023-10-14 M. Yusuf SarıgözHonor -ngl option for Cuda offloading in llava (#3621)
2023-10-13 Daniel Beveniusllama : remove n_threads from llama_decode_internal...
2023-10-13 slarenggml : add context enumeration functions (#3605)
2023-10-12 shibe2CLBlast: Fix matrix-vector multiplication (#3544)
2023-10-12 M. Yusuf Sarıgözexamples: support LLaVA v1.5 (multimodal model) (#3436)
2023-10-12 uint256_tdocs : fix typo GOMP_CPU_AFFINITY (#3597)
2023-10-12 Georgi Gerganovcmake : fix add_compile_options on macOS
2023-10-12 Ian Scrivenertypo : it is `--n-gpu-layers` not `--gpu-layers` (...
2023-10-12 Georgi Gerganovci : check if there is enough VRAM (#3596)
2023-10-12 Aarni Koskelaserver : add completion mode (no chat) (#3582)
2023-10-12 Georgi Gerganovprompts : add mnemonics.txt
2023-10-12 Georgi Gerganovserver : fix kv cache management (#3588)
2023-10-11 Georgi Gerganovmain : fix session loading bug (#3400)
2023-10-11 Michael Coppolaserver : add parameter -tb N, --threads-batch N (#3584)
2023-10-11 Kerfufflecommon : fix mirostat state when using multiple sequenc...
2023-10-11 Georgi Gerganovbatched : add bench tool (#3545)
2023-10-11 Zane Shannonexamples : add batched.swift + improve CI for swift...
2023-10-10 GalunidAdd MPT model to supported models in README.md (#3574)
2023-10-10 goerchMinor improvements in GPT2 tokenizer (#3567)
2023-10-10 Xingchen Song... readme : add bloom (#3570)
2023-10-10 Xingchen Song... llm : add bloom models (#3553)
2023-10-10 Jhen-Jie Hongswift : improvements and fixes (#3564)
2023-10-10 Jan Ploskillm : add MPT support (#3417)
2023-10-10 vvhg1infill. : fix tokenization (#3508)
2023-10-09 slarenggml-alloc : fix assert in debug builds (#3555)
2023-10-09 Georgi Gerganovrefact : fix convert script + zero out KV cache to...
2023-10-09 Georgi Gerganovmetal : do not use mul_mm kernels when ne00 < 64 (...
2023-10-08 Georgi Gerganovsync : ggml (ggml-backend) (#3548)
2023-10-08 Matheus C.... ci : add Zig CI/CD and fix build (#2996)
2023-10-08 Ryder Wishartapi_like_OAI.py : compat with Microsoft Guidance (...
2023-10-08 arcrankapi_like_OAI.py : simplify function (#2796)
2023-10-08 Johannes Rudolphk-quants : fix comments about block sizing (#3499)
2023-10-08 Georgi Gerganovci : enable on obj-c changes + fix metal build (#3540)
2023-10-08 Luo Tianzig : fix build by introducing train.cpp (#3539)
2023-10-08 Georgi Gerganovmetal : support MTLGPUFamily < Apple7, formatting,...
2023-10-08 Kerfufflellama : fix missing break in Persimmon arch case statem...
2023-10-07 KerfuffleFix trying to strip newline from empty prompt and cfg...
2023-10-07 M. Yusuf Sarıgözgguf.py : fix CI for publishing GGUF package (#3532)
2023-10-07 Tom Cpy : change version of numpy requirement to 1.24.4...
2023-10-07 cebtenzzrequantize : fail fast on write errors (#3521)
2023-10-07 Jhen-Jie Hongmetal : support default.metallib load & reuse code...
2023-10-07 Phillip Kravtsovllm : support Adept Persimmon 8B (#3410)
2023-10-07 goerchFix for #3454 (#3455)
2023-10-06 BarfingLemursreadme : update models, cuda + ppl instructions (#3510)
2023-10-06 Mihaiserver : docs fix default values and add n_probs (...
2023-10-06 Kerfufflekv cache slot search improvements (#3493)
2023-10-06 Georgi Gerganovprompts : fix editorconfig checks after #3416
2023-10-06 pudepiedjparallel : add option to load external prompt file...
2023-10-06 Jhen-Jie Hongserver : reuse llama_sample_token common util (#3494)
2023-10-06 l3utterflyllama : correct hparams comparison (#3446)
2023-10-06 Jhen-Jie Hongci : fix xcodebuild destinations (#3491)
2023-10-05 cebtenzzreconvert : update Falcon script for new HF config (...
2023-10-05 Kenvix ⭐build : use std::make_tuple() for compatibility with...
2023-10-05 staviqcommon : process escape sequences in reverse prompts...
2023-10-05 shibe2CLBlast: Fix handling of on-device tensor data
2023-10-05 Jhen-Jie Hongserver : fix incorrect num_tokens_predicted (#3480)
2023-10-05 Jhen-Jie Hongswift : disable ACCELERATE_NEW_LAPACK (#3481)
2023-10-05 Jhen-Jie Hongci : add swift build via xcodebuild (#3482)
2023-10-04 Kerfuffleconvert : fix Baichuan2 models by using vocab size...
2023-10-04 Georgi Gerganovreadme : add project status link
2023-10-04 Georgi Gerganovggml : fix build after #3329
2023-10-04 ds5t5llm : add Refact model (#3329)
2023-10-04 Georgi Gerganovsync : ggml (conv 1d + 2d updates, UB fixes) (#3468)
2023-10-04 Merrick Christensenfinetune : readme fix typo (#3465)
2023-10-03 Tameemggml : add RISC-V Vector Support for K-Quants and impro...
2023-10-03 h-h-h-hmain : consistent prefix/suffix coloring (#3425)
2023-10-03 Georgi Gerganovllama : fix session saving/loading (#3400)
2023-10-03 Alex Klinkhamerllama : expose model's rope_freq_scale in the API ...
2023-10-03 Jiahao Limetal : alibi for arbitrary number of heads (#3426)
2023-10-03 Evecmake : make LLAMA_NATIVE flag actually use the instruc...
2023-10-03 goerchWork on the BPE tokenizer (#3252)
2023-10-02 cebtenzzreconvert : fix vocab size when not defined in hparams...
2023-10-02 cebtenzzrecmake : increase minimum version for add_link_options...
next