]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-04-25 ddh0llama-quant : default ftype param `Q5_1` --> `Q8_0...
2026-04-25 Georgi Gerganovgitignore : add .pi + personal SYSTEM.md (#22316)
2026-04-25 Neo Zhang[SYCL] Optimize Q4_0 mul_mat for Arc770, add scripts...
2026-04-25 Reese Levineggml-webgpu: support for SSM_SCAN and disable set_rows...
2026-04-24 Piotr Wilkin... parser: fix structured output bug (#22302)
2026-04-24 Trivikram ReddyHexagon: Bump HMX Frequency to Max Corner (#22334)
2026-04-24 Shreya JainCI Snapdragon: Switch ubuntu-latest to ubuntu-slim...
2026-04-24 Zheyuan Chenggml-webgpu: enable FLASH_ATTN_EXT on browser without...
2026-04-24 Mengsheng Wuhexagon: use DIRID 13 in libggml-htp.inf for modern...
2026-04-24 Georgi Gerganovmetal : print GPU description (#22318)
2026-04-24 Adrien Gallouëtcommon : fix jinja warnings with clang 21 (#22313)
2026-04-24 Georgi Gerganovggml : minor coding style (#22308)
2026-04-24 Georgi Gerganovjinja : remove unused header (#22310)
2026-04-24 Georgi Gerganovserver : fix swa-full logic (#22288)
2026-04-24 Yes You Can... server: rename debug tags to match --cache-idle-slots...
2026-04-24 Mengsheng Wuhexagon: add SOLVE_TRI op (#21974)
2026-04-23 Chen Yuanfix(shader): handle the buffer aliasing for rms fuse...
2026-04-23 Ethan Turnercli: Remove redundant local sampling variables (#20429...
2026-04-23 Max Krasnyanskyhexagon: add support for basic and extended Op profilin...
2026-04-23 Shreya JainEnable testing on Snapdragon devices (#21051)
2026-04-23 srkizerserver : convert_anthropic_to_oai: also copy chat_templ...
2026-04-23 Song Liserver: fix heap-buffer-overflow from negative n_discar...
2026-04-23 Adrien Gallouëtvendor : update LibreSSL to 4.3.1 (#22285)
2026-04-23 kvc0server: (anthropic API) fix prefix caching (#21793)
2026-04-23 Sigbjørn Skjæretfix build number for sycl release (#22283)
2026-04-23 Daniel Beveniusmodel-conversion : fix mmproj output file name [no...
2026-04-23 Matthias Strakacli : cleanup auto-completion code (#21745)
2026-04-23 Tarek Dakhranserver: Enable transcriptions API for LFM2-Audio (...
2026-04-23 Georgi Gerganovmetal : fix event synchronization (#22260)
2026-04-23 Georgi Gerganovgitignore: add AGENTS.local.md (#22246)
2026-04-23 Georgi Gerganovggml-base: use MATH_LIBRARY variable instead of hardcod...
2026-04-23 Neo Zhang Jianyu[SYCL] Update oneapi 2025.3.3, Seperate SYCL build...
2026-04-23 ynankaniconvert : Handle ModelOpt produced mixed precision...
2026-04-23 abotsissycl : fused MoE mul_mat_vec_q for TG (#21920)
2026-04-23 Chen Yuanggml-webgpu: add support for im2col (#22259)
2026-04-23 Anav PrasadCUDA: fuse relu + sqr (#22249)
2026-04-23 uvosHIP: flip GGML_HIP_GRAPHS to default on (#22254)
2026-04-22 Nikhil Jain[WebGPU] Implement async tensor api and event api ...
2026-04-22 Masashi Yoshimuraggml-webgpu: Add fused RMS_NORM + MUL (#21983)
2026-04-22 Piotr Wilkin... chat: fix parallel_tool_calls default setting based...
2026-04-22 Georgi Gerganovspeculative-simple : add checkpoint support (#22227)
2026-04-22 Akarshan Biswassycl: Improve mul_mat_id memory efficiency and add...
2026-04-22 Xuan-Son Nguyenmtmd: also support LLAMA_ROPE_TYPE_NONE (#22242)
2026-04-22 Xuan-Son Nguyenserver: ignore reasoning content from transcription...
2026-04-22 manayangmtmd, llama : Update HunyuanVL vision-language model...
2026-04-22 Ethan Turnercommon: Refactoring sampler parameters (#20429) (#22233)
2026-04-22 Piotr Wilkin... common/chat, server: refactor, move all conversion...
2026-04-22 Chen Yuanggml-webgpu(shader): support conv2d kernels. (#21964)
2026-04-21 Aparna M Phexagon: add support for FILL op (#22198)
2026-04-21 Masashi Yoshimuraggml-webgpu: reset CPU/GPU profiling time when freeing...
2026-04-21 Xuan-Son Nguyenserver: allow cancel loading model (#21814)
2026-04-21 Shreya JainHexagon: DAIG op (#22195)
2026-04-21 Mengsheng Wuhexagon: fix missing v79 entry in libggml-htp.inf ...
2026-04-21 Paul Dubsspec : reset i_last when low acceptance streak occurs...
2026-04-21 Kwa Jie Haomtmd: Add support for Reka Edge 2603 (#21616)
2026-04-21 Georgi Gerganovarg : add --spec-default (#22223)
2026-04-21 Zijun Yuopenvino: driver setup, CI split, thread safety, and...
2026-04-21 Alessandro... vendor : update cpp-httplib to 0.43.1 (#22143)
2026-04-21 Georgi Gerganovmetal : workaround macOS GPU interactivity watchdog...
2026-04-21 Jeff Bolzvulkan: Support F16 OP_FILL (#22177)
2026-04-21 Xuan-Son Nguyenmtmd: correct mtmd_decode_use_mrope() (#22188)
2026-04-21 Georgi Gerganovllama-ext : fix exports (#22202)
2026-04-21 Georgi Gerganovsync : ggml
2026-04-21 Georgi Gerganovggml : bump version to 0.10.0 (ggml/1463)
2026-04-21 Georgi Gerganovfit-params : refactor + add option to output estimated...
2026-04-21 xris99server : fix hardcoded proxy connection timeout in...
2026-04-20 leonardHONGggml-cuda: flush legacy pool on OOM and retry (#22155)
2026-04-20 Xuan-Son Nguyenmtmd: correct get_n_pos / get_decoder_pos (#22175)
2026-04-20 Georgi Gerganovserver : remove /api endpoints (#22165)
2026-04-20 Gaurav GargTensor-parallel: Fix delayed AllReduce on Gemma-4 MoE...
2026-04-20 Johannes GäßlerTP: fix 0-sized tensor slices, AllReduce fallback ...
2026-04-20 pl752ggml-cpu: Optimized x86 and generic cpu q1_0 dot (follo...
2026-04-20 neha-haggml-webgpu: updated matrix-vector multiplication ...
2026-04-20 Xuan-Son Nguyenmtmd: refactor mtmd_decode_use_mrope (#22161)
2026-04-20 SamareshSinghfix: GLM-DSA crash in llama-tokenize when using vocab_o...
2026-04-20 Georgi Gerganovserver : refactor "use checkpoint" logic (#22114)
2026-04-20 Katostrofik[SYCL] Fix reorder MMVQ assert on unaligned vocab sizes...
2026-04-20 Yes You Can... server: rename --clear-idle to --cache-idle-slots ...
2026-04-19 Alessandro... vendor : update cpp-httplib to 0.42.0 (#21781)
2026-04-19 Johannes GäßlerCUDA: refactor mma data loading for AMD (#22051)
2026-04-19 Aldehir Rojascommon/autoparser : allow space after tool call (#22073)
2026-04-19 uvosHIP: Remove unesscary NCCL_CHECK (#21914)
2026-04-19 Xuan-Son Nguyenmtmd: add pos_0 to mtmd_image_tokens_get_decoder_pos...
2026-04-19 Gaurav Gargggml : reduce CPU overhead in meta backend (#22041)
2026-04-19 Sigbjørn Skjæretci : install spirv-headers for vulkan-cross (#22109)
2026-04-19 Dowonconvert : support sentence-transformer 5.4 config files...
2026-04-19 texasichcmake: remove CMP0194 policy to restore MSVC builds...
2026-04-19 Sascha Rogmannserver : speculative checkpointing (#19493)
2026-04-19 Radoslav Gerganovrpc : refactor the RPC transport (#21998)
2026-04-18 Cetarthoriphrosserver: Expose `media_tag` on /props endpoint. (#22028)
2026-04-18 Sigbjørn Skjæretmodel : refactor bias tensor variable names (#22079)
2026-04-18 Sigbjørn Skjæretandroid : libcommon -> libllama-common (#22076)
2026-04-18 SamareshSinghggml-backend-meta: add multi-segment read support in...
2026-04-18 Sigbjørn Skjæretci : free disk space for rocm release (#22012)
2026-04-18 Sigbjørn Skjæretconvert : fix (ignore for now) typings errors (#22002)
2026-04-18 Johannes Gäßlerllama: fit ctx size for CPU only (#21568)
2026-04-17 Reese Levineggml-webgpu: fix compiler warnings and refactor FlashAt...
2026-04-17 Aman GuptaCUDA: use LRU based eviction for cuda graphs (#21611)
2026-04-17 Yuri Khrustalevci : add android arm64 build and release (#21647)
2026-04-17 65amtmd: add missing struct tag (#22023)
next