]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-02-26 Sigbjørn SkjæretRefactor gguf scripts to improve metadata handling... gguf-v0.16.0
2025-02-26 Aleksei Nikiforovgguf-py: enable reading non-native endian files (#12081)
2025-02-26 Kante Yinreadme : update infra list (#9096)
2025-02-25 Olivier Chafikdocs: add docs/function-calling.md to lighten server...
2025-02-25 Jeff Bolzvulkan: fix assertion when qy_needs_dequant (#12068)
2025-02-25 rhjdvsgsgksserver: handle echo=false on /v1/completions (#12060)
2025-02-25 Juddadd OP sigmoid (#12056)
2025-02-25 Molly Sophiaggml-cpu: Fix build with sve (#12059)
2025-02-25 Rémy Ovulkan: implement more backpropagation operators (...
2025-02-25 Olivier Chafikserver: support add_generation_prompt query param ...
2025-02-25 Alex BrooksAdd Doc for Converting Granite Vision -> GGUF (#12006)
2025-02-25 Vitali Lovichllama : expose llama_model_n_head_kv in the API (#11997)
2025-02-25 Gian-Carlo... metal : copy kernels for quant to F32/F16 conversions...
2025-02-24 lhezopencl: fix for small models (#11950)
2025-02-24 Alex Brooksllava : Add Granite Vision Support (#11794)
2025-02-24 Neo Zhang Jianyu[SYCL] Optimize mul_mat for Q4_0 on Intel GPU (#12035)
2025-02-24 Aleksei Nikiforovgguf_convert_endian.py: implement byteswapping for...
2025-02-24 Akarshan BiswasSYCL: Fix GGML_SYCL_DEBUG macro (#11995)
2025-02-23 Florent BENOITrun: allow to customize prompt by env var LLAMA_PROMPT_...
2025-02-23 Eric CurtinSome llama-run cleanups (#11973)
2025-02-22 Aaron Teoggml-cpu: Support s390x SIMD Instruction Set (#12019)
2025-02-22 Johannes GäßlerCUDA: app option to compile without FlashAttention...
2025-02-22 Ting Loullava: build clip image from pixels (#11999)
2025-02-22 Georgi Gerganovci : fix arm upload artifacts (#12024)
2025-02-22 Johannes GäßlerCUDA: optimize FA for GQA + large batches (#12014)
2025-02-22 Rohanjames1997ci : Build on Github-hosted arm64 runners (#12009)
2025-02-22 Georgi Gerganovserver : disable Nagle's algorithm (#12020)
2025-02-22 Gian-Carlo... cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion...
2025-02-22 Daniel Beveniusllama.swiftui : add "Done" dismiss button to help view...
2025-02-21 Georgi Gerganovllama : skip loading unused tensors (#12004)
2025-02-21 Johannes Gäßlerdoc: update contributing guidelines [no ci] (#11969)
2025-02-21 PureJourneyCUDA: correct the lowest Maxwell supported by CUDA...
2025-02-21 BodhiMUSA: support ARM64 and enable dp4a .etc (#11843)
2025-02-21 Alex Brooksclip : fix visual encoders with no CLS (#11982)
2025-02-20 momongaserver (webui): Fix Premature Submission During IME...
2025-02-20 Charles Xuggml-cpu: Add CPU backend support for KleidiAI library...
2025-02-20 Prashant Vithuleggml: aarch64: implement SVE kernels for q3_K_q8_K...
2025-02-20 Michael Engelrun : add --chat-template-file (#11961)
2025-02-19 Johannes Gäßlerdoc: add links to ggml examples [no ci] (#11958)
2025-02-19 Daniel Beveniuscommon : add llama.vim preset for Qwen2.5 Coder (#11945)
2025-02-19 Georgi Gerganovspeculative : update default params (#11954)
2025-02-19 Daniel Beveniusllama : fix indentation in llama-grammar [no ci] (...
2025-02-18 igardevserver : (webui) Enable communication with parent html...
2025-02-18 Olivier Chafiktool-call: refactor common chat / tool-call api (+...
2025-02-18 Xuan-Son Nguyenserver : add TEI API format for /rerank endpoint (...
2025-02-18 MoonRide303scripts: corrected encoding when getting chat template...
2025-02-18 xiaobing318docs : Fix duplicated file extension in test command...
2025-02-17 Johannes GäßlerCUDA: use async data loading for FlashAttention (#11894)
2025-02-17 Eveupdate release requirements (#11897)
2025-02-17 Antoine Viallonserver : fix divide-by-zero in metrics reporting (...
2025-02-17 Rémy Ovulkan: implement several ops relevant for ggml_opt...
2025-02-16 Xuan-Son Nguyenserver : bump httplib to 0.19.0 (#11908)
2025-02-16 standby24x7common : Fix a typo in help (#11899)
2025-02-16 Xuan-Son Nguyenci : fix (again) arm64 build fails (#11895)
2025-02-16 Jeff Bolzvulkan: support multi/vision rope, and noncontiguous...
2025-02-16 Hale Chanmetal : fix the crash caused by the lack of residency...
2025-02-15 Johannes Gäßlerscripts: fix compare-llama-bench commit hash logic...
2025-02-15 708-145examples: fix typo in imatrix/README.md (#11884)
2025-02-15 Adrian Kretzmetal : optimize dequant q6_K kernel (#11892)
2025-02-15 Georgi Gerganovreadme : add notice about new package registry (#11890)
2025-02-15 Georgi Gerganovrepo : update links to new url (#11886)
2025-02-15 Olivier Chafikserver: fix type promotion typo causing crashes w/...
2025-02-15 Rémy Ovulkan: initial support for IQ1_S and IQ1_M quantizatio...
2025-02-14 Michał Moskalllguidance build fixes for Windows (#11664) upstream/0.0.4719
2025-02-14 lhezopencl: Fix rope and softmax (#11833)
2025-02-14 Diego Devesacuda : add ampere to the list of default architectures...
2025-02-14 Georgi Gerganovdocker : drop to CUDA 12.4 (#11869)
2025-02-14 Daniel Beveniusllama : add completion for --chat-template-file (#11860)
2025-02-14 Jinyang Heggml: optimize some vec dot functions for LoongArch...
2025-02-14 Evevulkan: linux builds + small subgroup size fixes (...
2025-02-14 theraininskyllama-bench : fix unexpected global variable initialize...
2025-02-13 Georgi Gerganovreadme : minor
2025-02-13 Jeffrey Morganllamafile: use member variable instead of constant...
2025-02-13 Reza Rahemtolaserver : (docs) Update wrong tool calling example ...
2025-02-13 Daniel Beveniusllama : add --completion-bash option (#11846)
2025-02-13 R0CKSTARmusa: bump MUSA SDK version to rc3.1.1 (#11822)
2025-02-13 Olivier Chafik`server`: fix tool-call of DeepSeek R1 Qwen, return...
2025-02-13 Vinesh Janarthanansampling: add Top-nσ sampler (#11223)
2025-02-13 Oleksandr Kuvshynovllama.cpp: fix warning message (#11839)
2025-02-13 Daniel Beveniusllama : update llama_decode_internal ref [no ci] (...
2025-02-13 Diego Devesaggml-cpu : add chunking support to mul_mat_id (#11666)
2025-02-12 Xuan-Son Nguyenggml : x2 speed for WASM by optimizing SIMD (#11453)
2025-02-12 Woof Dogserver : (webui) Give copy button back to all message...
2025-02-12 uvosHIP: Remove GCN from list of devices that avoid MMQ...
2025-02-12 JCFix: Compile failure due to Microsoft STL breaking...
2025-02-12 Georgi Gerganovsync : ggml
2025-02-12 uvosHIP: Switch to std::vector in rocblas version check...
2025-02-12 bandoticleanup: fix compile warnings associated with gnu_print...
2025-02-12 Richardggml : fix multi-threaded clamp_f32 (#11824)
2025-02-12 Weizhao Ouyangggml-cpu: Fix duplicate MATMUL_INT8 (#11817)
2025-02-12 Johannes GäßlerCUDA: fix CUDART_VERSION checks (#11821)
2025-02-12 Daniel Beveniusllama : fix typo in llama-grammar.h [no ci] (#11816)
2025-02-11 lhezdocs: add OpenCL (#11697)
2025-02-11 Sheldon RobinsonFix #11802: Compile bug - RegQueryValueExA changed...
2025-02-11 Daniel Beveniusserver : use common_token_to_piece instead of common_de...
2025-02-10 Johannes GäßlerCUDA: use arch list for compatibility check (#11775)
2025-02-10 Maxim Evtushfix: typos in documentation files (#11791)
2025-02-10 jason_wdocs: utilize the forward slash (/) as the path separat...
2025-02-10 Xuan-Son Nguyenserver : (webui) introduce conversation branching ...
2025-02-10 Wilken Gottwaltllama-mmap: fix missing include (#11796)
next