]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-05-30 Meng, Hengyu[SYCL] fix intel docker (#7630)
2024-05-30 Galunidgguf-py : Add tokenizer.ggml.pre to gguf-new-metadata...
2024-05-29 Georgi Gerganovmetal : remove invalid asserts (#7617)
2024-05-29 Georgi Gerganovmetal : add missing asserts (#7617)
2024-05-29 Georgi Gerganovggml : fix YARN + add tests + add asserts (#7617)
2024-05-29 Georgi Gerganovcuda : non-cont concat support (#7610)
2024-05-29 Radoslav Gerganovllama-bench : add support for the RPC backend (#7435)
2024-05-29 slarenggml : use atomic_flag for critical section (#7598)
2024-05-29 Georgi Gerganovscripts : remove mpi remnants
2024-05-29 Georgi Gerganovsync : ggml
2024-05-29 Georgi Gerganovggml : restore ggml_rope_xpos_inplace (ggml/0)
2024-05-29 Akarshan BiswasAdd Arc A750 and Arch linux to readme-sycl.md as verifi...
2024-05-29 zhouwgggml : fix typo in ggml.c (#7603)
2024-05-28 Meng, Hengyu[SYCL] Align GEMM dispatch (#7566)
2024-05-28 jaime-m-pTokenizer WPM fixes (#7500)
2024-05-28 Georgi Gerganovsycl : fix assert (#7563)
2024-05-28 Giuseppe Scrivanollama : support small Granite models (#7481)
2024-05-28 k.h.laivulkan: properly initialize vulkan devices for LLAMA_SP...
2024-05-28 Radoslav Gerganovrpc : resource management rework (#7562)
2024-05-28 fairydreamingAdd support for DeepseekV2ForCausalLM (#7519)
2024-05-28 Georgi Gerganovtests : fix test-tokenizer-0.sh
2024-05-28 Georgi Gerganovllama : handle unknown utf8 bytes (#7588)
2024-05-28 Briangithub: add refactor to issue template (#7561)
2024-05-28 Neo Zhang[SYCL]fix ggml_sycl_mul_mat_id() to match the change...
2024-05-28 Georgi Gerganovggml : generalize GGML_OP_CONCAT (#7563)
2024-05-28 mgroeber9110server: do not remove whitespace at the start of a...
2024-05-28 Nathan EpsteinMarkdownish code block fix (#7571)
2024-05-28 Ikko Eltociear... llava : update clip.h (#7580)
2024-05-27 Djip007update HIP_UMA #7399 (#7414)
2024-05-27 kunnisadding in x64 targets to cmake presets (#7574)
2024-05-27 Johannes Gäßlermake: add --device-debug to NVCC debug flags (#7542)
2024-05-27 agray3Allow multiple copy function pointers for CUDA graph...
2024-05-27 AidanBeltonSFix q_xxs using mul_mat_q (#7459)
2024-05-27 AidanBeltonSAdd freq factors (#7495)
2024-05-27 Georgi Gerganovmetal : add GGML_OP_REPEAT kernels (#7557)
2024-05-27 Georgi Gerganovmetal : disable FA kernel for HS=256 (#7556)
2024-05-27 Georgi Gerganovllama : add comments about experimental flags (#7544)
2024-05-27 Briangithub: add self sorted issue ticket forms (#7543)
2024-05-26 Georgi Gerganovflake.lock: Update (#7540)
2024-05-26 Brianmain: replace --no-special with --special (#7534)
2024-05-26 GalunidFix aya-23 conversion scripts (#7539)
2024-05-26 Bartowskillama : add Smaug 70B support (#7402)
2024-05-26 Aarni KoskelaReadme: add akx/ggify to tools (#1484)
2024-05-26 HanishKVCSimpleChat Completion Mode flexibility and cleanup...
2024-05-25 Georgi Gerganovtrain : change default FA argument (#7528)
2024-05-25 Brianlabeler: added Apple Metal detector (+Kompute) (#7529)
2024-05-25 Justine Tunneymain : don't print special tokens with --grammar (...
2024-05-25 Masaya, Katoggml: aarch64: SVE kernels for q8_0_q8_0, q4_0_q8_0...
2024-05-25 Elton Kolaandroid : module (#7502)
2024-05-25 Xuan Son Nguyenfix missing slash in `fs_get_cache_directory()` (#7503)
2024-05-25 Mikko JuolaMake tokenize CLI tool have nicer command line argument...
2024-05-25 compiladegguf-py : fix and simplify quantized shape round-trip...
2024-05-24 Georgi Gerganovflake.lock: Update (#7232)
2024-05-24 Briandocker.yml: disable light-intel and server-intel test...
2024-05-24 fairydreamingAdd support for ArcticForCausalLM (#7020)
2024-05-24 Neo Zhangadd build shared lib in win release package (#7438)
2024-05-23 Georgi Gerganovreadme : remove trailing space (#7469)
2024-05-23 Georgi Gerganovggml : silence UB sanitizer error during iq2_xxs quanti...
2024-05-23 Tristan DruyenFix phi3 chat template confusion with zephyr (#7449)
2024-05-23 Raj Hammeer... readme : add Bunny in supported models [no ci] (#7469)
2024-05-23 Daniel Beveniusllama : add getters for n_threads/n_threads_batch ...
2024-05-23 Georgi Gerganovci : use Pythia models instead of OpenLlama (#7470)
2024-05-23 Victor Nogueirareadme : add GPT-NeoX + Pythia to the list of supported...
2024-05-23 fairydreamingAdd missing inference support for GPTNeoXForCausalLM...
2024-05-23 Georgi Gerganovllama : rename n_ctx -> cache.size, less confusing...
2024-05-23 Brianlabeler.yml: add embedding label detector [no ci] ...
2024-05-23 Georgi Gerganovggml : remove ggml_flash_attn and ggml_flash_ff (#7463)
2024-05-23 Georgi Gerganovggml : drop support for QK_K=64 (#7473)
2024-05-23 0cc4mUpdate vulkan rope implementation to support frequency...
2024-05-23 Georgi Gerganovmain : minor (#7462)
2024-05-22 Johannes GäßlerCUDA: fix FA out-of-bounds reads (#7479)
2024-05-22 HanishKVCSimpleChat: a simple and dumb web front end for testing...
2024-05-22 Georgi Gerganovbuild : remove zig (#7471)
2024-05-22 Georgi Gerganovcommon : normalize naming style (#7462)
2024-05-22 Johannes GäßlerCUDA: fix FA out-of-bounds writes (#7465)
2024-05-22 slarenphi3 : duplicate rope factors in each layer (#7447)
2024-05-22 k.h.laivulkan: add workaround for iterator boundary check...
2024-05-22 Justine Tunneyllama : add missing model type names (#7445)
2024-05-22 Georgi Gerganovcuda : fix compile warning (#7454)
2024-05-22 Johannes GäßlerCUDA: remove incorrect precision check (#7454)
2024-05-22 Georgi Gerganovcuda : fix rope + add tests (#7452)
2024-05-21 liuwei-gitllama : add phi3 128K model support (#7225)
2024-05-21 Georgi Gerganovmetal : handle F16 inf values, fix FA partial offload...
2024-05-21 Olivier Chafik`grammars`: fix resampling logic regression (#7424)
2024-05-21 Johannes GäßlerCUDA: fix unused warning in mmq.cu (#7442)
2024-05-21 Georgi Gerganovtests : test-tokenizer-0.sh print more info (#7402)
2024-05-21 Amirexamples: cache hf model when --model not provided...
2024-05-21 Johannes GäßlerCUDA: deduplicate mmq code (#7397)
2024-05-21 jaime-m-pTokenizer SPM fixes for phi-3 and llama-spm (bugfix...
2024-05-20 jaime-m-pTokenizer SPM fixes for phi-3 and llama-spm (#7375)
2024-05-20 Georgi Gerganovllama : remove Persimmon (#7408)
2024-05-20 Johannes Gäßlerperplexity: update README FP16 results [no ci] (#7413)
2024-05-20 Radoslav Gerganovrpc : track allocated buffers (#7411)
2024-05-20 Georgi Gerganovserver : fix temperature + disable some tests (#7409)
2024-05-20 AidanBeltonS[SYCL] Update SYCL upscale operation (#7321)
2024-05-20 BinganUpdate README.md (#7410)
2024-05-20 Herman Semenovggml-opencl, llama: using reserve() if count already...
2024-05-20 junchao-loongsonggml : add loongarch lsx and lasx support (#6454)
2024-05-20 Georgi Gerganovserver : tuning tests (#7388)
2024-05-20 Georgi Gerganovserver : return error on too large embedding input...
next