]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-09-21 Huang QiCI: Provide prebuilt windows binary for hip (#9467)
2024-09-20 slarenquantize : improve type name parsing (#9570)
2024-09-20 Georgi Gerganovggml : fix builds (#0)
2024-09-20 Georgi Gerganovggml : fix trailing whitespace (#0)
2024-09-20 Georgi Gerganovsync : ggml
2024-09-20 Johannes Gäßlerggml/examples: add backend support for numerical optimi...
2024-09-20 Georgi Gerganovexamples : add null threadpool args where needed (ggml/0)
2024-09-20 Johannes GäßlerCUDA: fix sum.cu compilation for CUDA < 11.7 (#9562)
2024-09-20 Georgi Gerganovexamples : flush log upon ctrl+c (#9559)
2024-09-20 Sigbjørn Skjæretperplexity : do not escape input data by default (...
2024-09-19 Georgi Gerganovserver : clean-up completed tasks from waiting list...
2024-09-19 Sigbjørn Skjæretimatrix : disable prompt escape by default (#9543)
2024-09-18 slarenggml : fix n_threads_cur initialization with one thread...
2024-09-18 Georgi Gerganovscripts : verify py deps at the start of compare (...
2024-09-18 Daniel Beveniusllama : use reserve/emplace_back in sampler_sample...
2024-09-18 Vinesh Janarthananserver : match OAI structured output response (#9527)
2024-09-18 Eric Zhangserver : fix OpenSSL build (remove obsolete `LOG_INFO...
2024-09-18 Neo Zhang Jianyu[SYCL]set context default value to avoid memory issue...
2024-09-17 Michael Podvitskiyllama-bench: correct argument parsing error message...
2024-09-17 Bert Wagnerarg : add env variable for parallel (#9513)
2024-09-17 Michael Podvitskiyllama : fix n_vocab init for 'no_vocab' case (#9511)
2024-09-17 Max Krasnyanskythreadpool : skip polling for unused threads (#9461)
2024-09-17 Yuri Khrustalevunicode : add <algorithm> (#9508)
2024-09-17 Gabe Goodhartllama : support IBM Granite architecture (#9412)
2024-09-17 Michael Podvitskiyllama : add llama_n_head() (#9512)
2024-09-16 slarenggml : move common CPU backend impl to new header ...
2024-09-16 Daniel Beveniusllama : rename n_embed to n_embd in rwkv6_time_mix...
2024-09-16 Michael Podvitskiyggml : link MATH_LIBRARY not by its full path (#9339)
2024-09-16 compiladeconvert : identify missing model files (#9397)
2024-09-16 Georgi Gerganovcmake : do not hide GGML options + rename option (...
2024-09-16 Eveggml : IQ4_NL sgemm + Q4_0 AVX optimization (#9422)
2024-09-16 Shane Allama : support OLMoE (#9462)
2024-09-16 CarryFunllama : support MiniCPM3 (#9322)
2024-09-16 Vinesh Janarthananmain : option to disable context shift (#9484)
2024-09-16 Georgi Gerganovmetal : handle zero-sized allocs (#9466)
2024-09-16 Georgi Gerganovflake.lock: Update (#9488)
2024-09-15 Georgi Gerganovcommon : reimplement logging (#9418)
2024-09-15 slarengguf-split : add basic checks (#9499)
2024-09-15 Michael Podvitskiycmake : correct order of sycl flags (#9497)
2024-09-15 Csaba Kecskemetipy : add "LLaMAForCausalLM" conversion support (#9485)
2024-09-15 OSecretreadme : update tools list (#9475)
2024-09-15 Michael Podvitskiycmake : try to fix sycl+intel build (#9487)
2024-09-14 Yuri Khrustalevggml : ggml_type_name return "NONE" for invalid values...
2024-09-14 VoidIsVoidserver: add data: [DONE] to /chat/completions stream...
2024-09-14 Georgi Gerganovcmake : use list(APPEND ...) instead of set() + dedup...
2024-09-14 Daniel Beveniusllama : make cell_id const in inp_s_mask block (#9470)
2024-09-13 Xuan Son Nguyenserver : add loading html page while model is loading...
2024-09-13 Georgi Gerganovllama : llama_perf + option to disable timings during...
2024-09-13 Gilad S.feat: remove a sampler from a chain (#9445)
2024-09-12 Mathijs Henquetserver : Add option to return token pieces in /tokenize...
2024-09-12 Dou Xinpengcann: Add host buffer type for Ascend NPU (#9406)
2024-09-12 fengerhu1llava : fix the script error in MobileVLM README (...
2024-09-12 Xuan Son Nguyenlora : raise error if lm_head is ignored (#9103)
2024-09-12 Michael Podvitskiycmake : fix for builds without `GGML_CDEF_PUBLIC` ...
2024-09-12 Huang Qici : update HIP SDK to 24.Q3 (ROCm 6.1) (#9329)
2024-09-12 daminhopy : add Phi-1.5/Phi-2 tokenizer (#9361)
2024-09-12 Trivikram Kamatci : bump actions/checkout to v4 (#9377)
2024-09-12 Michael Podvitskiycmake : fixed the order of linking libraries for llama...
2024-09-12 Molly Sophiapy : add special tokens in hf_converter for RWKV v6...
2024-09-12 Ahmad Tameemriscv : modify Makefile and add a RISCV_VECT to print...
2024-09-12 Georgi Gerganovggml : hide ggml_object, ggml_cgraph, ggml_hash_set...
2024-09-12 Neo Zhang Jianyuenhance run script to be easy to change the parameters...
2024-09-12 Xinpeng Doucann: Fix error when running a non-exist op (#9424)
2024-09-12 Faisal ZaghloulAdd Jais to list of supported models (#9439)
2024-09-11 slarenllama : skip token bounds check when evaluating embeddi...
2024-09-11 Pavel Zloipy : support converting local models (#7547)
2024-09-11 Xuan Son Nguyenllava : correct args for minicpmv-cli (#9429)
2024-09-11 Xuan Son Nguyenfiles : remove accidentally added `lora_test` submodule...
2024-09-11 Farbod Bijaryfeat: Implements retrying logic for downloading models...
2024-09-11 Johannes GäßlerCUDA: fix --split-mode row race condition (#9413)
2024-09-11 Georgi Gerganovbatched-bench : remove unused code (#9305)
2024-09-11 R0CKSTARmusa: remove Clang builtins mapping (#9421)
2024-09-11 Alberto Cabrera... sycl : update support conditions (#9394)
2024-09-10 Georgi Gerganovflake.lock: Update (#9360)
2024-09-10 Xuan Son Nguyenarg : bring back missing ifdef (#9411)
2024-09-10 matteoenable --special arg for llama-server (#9419)
2024-09-10 slarenllama : move random seed generation to the samplers...
2024-09-10 Georgi Gerganovmetal : fix compile warning with GGML_METAL_NDEBUG...
2024-09-10 Daniel Beveniusllama : update llm_build_copy_mask_state comment [no...
2024-09-10 Molly SophiaRWKV v6: Add time_mix_decay_w1/w2 in quant exclusion...
2024-09-10 slarenmake : do not run llama-gen-docs when building (#9399)
2024-09-09 Xuan Son Nguyencommon : move arg parser code to `arg.cpp` (#9388)
2024-09-09 Radoslav Gerganovrpc : fix segfault with nkvo (#9389)
2024-09-09 Prashant Vithuleggml : vector length agnostic SVE support (#9290)
2024-09-09 slarenllama : minor sampling refactor (2) (#9386)
2024-09-09 Georgi Gerganovreadme : update hot topics
2024-09-09 Johannes GäßlerCUDA: fix variable name conflict for Windows build...
2024-09-09 Antonis Makropoulosreadme : add LLMUnity to UI projects (#9381)
2024-09-09 Radoslav Gerganovrpc : update README [no ci] (#9320)
2024-09-09 Dan JohanssonArm AArch64: Documentation updates (#9321)
2024-09-08 Markus TavenrathOverlap cmdbuffer creation and cmdbuffer execution...
2024-09-08 Georgi Gerganovcuda : fix FA Q src index (1 -> 0) (#9374)
2024-09-08 Xuan Son Nguyencommon : bring back missing args, add env var duplicati...
2024-09-08 slarencommon : restore --n-gpu-layers (#9371)
2024-09-08 slarenllama : refactor samplers internal implementation ...
2024-09-08 Neo Zhang Jianyu[SYCL] add check malloc result on device (#9346)
2024-09-08 slarenllama : sanitize tokens in the upper bound (#9359)
2024-09-08 Xuan Son Nguyenimatrix : fix arg parser for imatrix (#9366)
2024-09-08 Georgi Gerganovmetal : update support condition for im2col + fix warni...
2024-09-08 Georgi Gerganovsync : ggml
next