]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-12-17 Sigbjørn Skjæretci : clean up webui jobs (#18116)
2025-12-17 Pascalcommon: fix --override-kv to support comma-separated...
2025-12-17 yuloHIP: Refactor mma for RDNA and CDNA (#17990)
2025-12-17 Naco Sirenllama.android : Rewrite Android binding (w/o cpu_featur... upstream/0.0.7446
2025-12-17 TrevorSarg: allow -kvu flag for llama-perplexity (#18117)
2025-12-17 Aadeshveer... ggml : use WARP_SIZE/2 for argmax reduction offset...
2025-12-17 Yuri Khrustalevgguf-py : allow converting multi-tensor models from...
2025-12-16 Johannes Gäßlerllama-fit-params: force disable mlock (#18103)
2025-12-16 Johannes Gäßlerllama-fit-params: lower ctx size for multi GPU (#18101)
2025-12-16 Johannes Gäßlerllama-fit-params: fix underflow for dense models (...
2025-12-16 Johannes Gäßlerllama-fit-params: QoL impr. for prints/errors (#18089)
2025-12-16 Xuan-Son Nguyenmodel: fix LFM2 missing tensors (#18105)
2025-12-16 Johannes Gäßlerllama: fix early stop in params_fit if ctx is set ...
2025-12-16 yifant-codeserver: fix crash when batch > ubatch with embeddings...
2025-12-16 Daniel Beveniusmodel-conversion : remove -fa option in model card...
2025-12-16 Xuan-Son Nguyenarch: refactor LLM_TENSOR_NAMES (#18051)
2025-12-16 Xuan-Son Nguyenarg: clarify auto kvu/np being set on server (#17997)
2025-12-16 Piotr Wilkin... Optimization: Qwen3 next autoregressive pass (#17996)
2025-12-16 Andrew AladjevCLI: fixed adding cli and completion into docker contai...
2025-12-16 2114L3server: Update README.md incorrect argument (#18073)
2025-12-16 Xuan-Son Nguyenmodel: support GLM4V vision encoder (#18042)
2025-12-16 Daniel Beveniusmodel-conversion : add note about verifying previous...
2025-12-16 Daniel Beveniusmodel-conversion : use CONVERTED_EMBEDDING_MODEL for...
2025-12-16 Aldehir Rojascommon : add nemotron 3 parsing (#18077)
2025-12-16 Francisco Herreraadded note for old Intel hardware pre sycl (#18017)
2025-12-16 Georgi Gerganovsecurity : add collaborator guidance (#18081)
2025-12-16 Chris Petersonllama: Include algorithm header needed for C++23 (...
2025-12-16 Georgi Gerganovgraph : reuse SSM graphs (#16490)
2025-12-16 Sigbjørn Skjæretci : separate webui from server (#18072)
2025-12-16 Aleksander... webui: Improve copy to clipboard with text attachments...
2025-12-16 Aleksander... webui: Add setting to always show sidebar on Desktop...
2025-12-16 Daniel Beveniusllama : add support for NVIDIA Nemotron 3 Nano (#18058)
2025-12-16 Darius LukasWebui: Disable attachment button and model selector...
2025-12-15 Sigbjørn Skjæretconvert : move rope_parameters to TextModel class ...
2025-12-15 Shouyuggml-hexagon: mm for mtmd (#17894)
2025-12-15 HelloKSmodel : add KORMo model (#18032)
2025-12-15 ssweenskv-cache: Fix state restore fragmented cache (#17982)
2025-12-15 PascalFix unreadable user markdown colors and truncate long...
2025-12-15 Jeremy Demeulemetal: use shared buffers on eGPU (#17866)
2025-12-15 Xuan-Son Nguyenmtmd: refactor audio preprocessing (#17978)
2025-12-15 Andrew Aladjevcli: fixed dead links to tools/main for cli and complet...
2025-12-15 Thomas Jaroschwebui: add "delete all conversations" button to import...
2025-12-15 Johannes Gäßlerllama: automatically set parameters not set by the...
2025-12-15 Neo Zhang Jianyu[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4...
2025-12-15 piDackmodel : add glm-asr support (#17901)
2025-12-14 Xuan-Son Nguyenpreset: handle negated arg, reverse the meaning if...
2025-12-14 Sigbjørn Skjæretconvert : refactor rope scaling handling (#18013)
2025-12-14 Haowei Wumtmd: enhance image resizing in llava_uhd (#18014)
2025-12-14 Ruben Ortlamvulkan: fix mul_mat_vec_iq1_s formatting (#18026)
2025-12-14 Xuan-Son Nguyengraph: add f_attn_temp_offset (#18025)
2025-12-14 Georgi Gerganovcommon : refactor common_sampler + grammar logic change...
2025-12-14 Jeff Bolzvulkan: Fix data race/hang in scalar/cm1 flash attentio...
2025-12-14 lovedheartvulkan: improve mul_mat_vec_iq1_s speed (#17874)
2025-12-14 Evevulkan: faster q6_k matmul (#17813)
2025-12-14 Georgi Gerganovmodel-conversion : cast logits to float32 (#18009)
2025-12-14 Georgi Gerganovmodels : fix YaRN regression + consolidate logic (...
2025-12-14 Georgi Gerganovggml : arm repack fix build
2025-12-14 Georgi Gerganovsync : ggml
2025-12-14 Georgi Gerganovggml : arm repack fix build (whisper/0)
2025-12-14 Congcong Caicmake : set `CMAKE_RUNTIME_OUTPUT_DIRECTORY` for non...
2025-12-13 Xuan-Son Nguyenscripts: add script to compare logprobs of llama.cpp...
2025-12-13 Sergey Fedorovserver-models.cpp: add missing <filesystem> (#18000)
2025-12-13 Jeff Bolzllama_context: synchronize before reallocating output...
2025-12-13 Xuan-Son Nguyenarg: fix common_params_parse not accepting negated...
2025-12-13 Gustavo Rocha... cmake: correct scope - link ws2_32 for MinGW/w64devkit...
2025-12-13 Jeff Bolzvulkan: support get_rows for i32 (#17941)
2025-12-13 Jeff Bolzvulkan: support GGML_OP_DIAG (#17893)
2025-12-13 Jeff Bolzvulkan: Multi-pass softmax for large number of cols...
2025-12-13 Georgi Gerganovspeculative-simple : free batch on exit (#17985)
2025-12-13 Sigbjørn Skjæretcommon : skip model validation when --completion-bash...
2025-12-13 Jeff Bolzvulkan: Allow non-pow2 n_experts in topk_moe (#17872)
2025-12-13 Sigbjørn Skjæretadd llama-completion to completion-bash executables...
2025-12-13 Daniel Beveniusmodel-conversion : use CONVERTED_MODEL value for conver...
2025-12-12 Xuan-Son Nguyencommon: support negated args (#17919)
2025-12-12 Xuan-Son Nguyenclip: move model cgraphs into their own files (#17965)
2025-12-12 jiahao suci : change the cann version and the container pull...
2025-12-12 Sigbjørn Skjæretdocker : include legacy llama-completion binary (#17964)
2025-12-12 Johannes GäßlerCUDA: fix overflow in MMA kernel without stream-k ...
2025-12-12 Georgi Gerganovmodels : fix the attn_factor for mistral3 graphs +...
2025-12-12 Sigbjørn Skjæretcann : fix ops broken by circular padding guard (#17825)
2025-12-12 ixgbeggml-cpu : fix RISC-V Q4_0 repack select and RVV featur...
2025-12-12 Xuan-Son Nguyenmtmd: explicitly forbidden inclusion of private header...
2025-12-12 Aleksander... webui: Fix parsing non-LaTeX occurrencies of `\(` or...
2025-12-12 Xuan-Son Nguyenarg: add -mm and -mmu as short form of --mmproj and...
2025-12-12 Daniel Beveniusmodel-conversion : remove max diff check in compare...
2025-12-12 Adrien Gallouëtcommon : add minimalist multi-thread progress bar ...
2025-12-12 Gustavo Rocha... cmake: link ws2_32 for MinGW/w64devkit builds in cpp...
2025-12-12 yuloHIP: enable mmf for RDNA3 (#17879)
2025-12-11 PascalAdd a search field on model selector / improve mobile...
2025-12-11 Piotr Wilkin... SOLVE_TRI extension to more dimensions (#17793)
2025-12-11 Georgi Gerganovggml-alloc : fix reuse-parent logic for misaligned...
2025-12-11 Georgi Gerganovbatch : fix sequence id ownership (#17915)
2025-12-11 Yuichiro Utsumidocs: use port 8080 in Docker examples (#17903)
2025-12-10 nullnameggml-hexagon: fix `rope` failure at `test-backend-ops...
2025-12-10 Sigbjørn Skjæretci: fix riscv64-native build (#17916)
2025-12-10 Xuan-Son Nguyenmtmd: some small clean up (#17909)
2025-12-10 Xuan-Son Nguyencli: enable jinja by default (#17911)
2025-12-10 Pascalserver: add presets (config) when using multiple models...
2025-12-10 Max KrasnyanskyFix race conditions in threadpool when dealing with...
2025-12-10 Georgi Gerganovggml : remove GGML_KQ_MASK_PAD constant (#17910)
next