]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-05-19 Georgi Gerganovllama : MTP clean-up (#23269)
2026-05-19 Aleksander... ui: Bump packages + address build warnings (#23300)
2026-05-19 Sigbjørn Skjæretci : install libssl-dev (#23325)
2026-05-19 Sigbjørn Skjæretci : install server kleidiai runner dependencies (...
2026-05-19 Pascalserver-context: guarantee there is at least 1 token...
2026-05-19 Georgi Gerganovserver : print graphs reused in slot timings (#23279)
2026-05-19 Georgi Gerganovsave-load-state : refactor tests and improve readabilit...
2026-05-19 Georgi Gerganovllama-eval : add per-task summary stats (#23151)
2026-05-19 Reese Levineggml-webgpu : extend GDN for K>1 (#23299)
2026-05-19 Neo Zhang[SCYL] add chapter for performance reference in SYCL...
2026-05-19 Sigbjørn Skjæretconvert : filter lora tensor names (#23077)
2026-05-19 Intel AI Get... sycl: add GGML_SYCL_USE_ASYNC_MEM_OP env toggle (#22153)
2026-05-19 Radoslav Gerganovrpc : keep last_graph_uid in the device context (#23273)
2026-05-18 Pranav Dhinakarhexagon: add support for TRI op (#22822)
2026-05-18 Pranav Dhinakarggml-hexagon: add PAD op HVX kernel (#23078)
2026-05-18 SamareshSinghdocker : add OCI image labels for version and build...
2026-05-18 Adrien Gallouëtcommon : remove hf cache migration (#23266)
2026-05-18 Aleksander... ui: Update KaTeX package and clean up logs from `sass...
2026-05-18 Aleksander... feat: add scroll-to-bottom button to chat + prevent...
2026-05-18 Aleksander... ui: Refactor models store, MCP service, and gate logs...
2026-05-18 Aleksander... ui: Centralize monospace font styles in app.css (#23272)
2026-05-18 Martin Anderssonwebui: fix Tailwind v4 utility classes missing when...
2026-05-18 Andreillama: initialize pre-norm embedding mask flag (#23256)
2026-05-18 Sigbjørn Skjæretadd myself to conversion (#23261)
2026-05-18 Martin Klacerci : added kleidiai-server to server-self-hosted workfl...
2026-05-18 Georgi Gerganovscripts : allow wc2wt with an existing branch (#23189)
2026-05-18 Intel AI Get... sycl: scalar SWAR byte-subtract in Q6_K MMVQ dot produc...
2026-05-18 Intel AI Get... sycl: route small f32 matmuls to oneMKL, bypass oneDNN...
2026-05-18 Neo Zhangsycl : fix error when use -mg 1 error (#23140)
2026-05-18 Incarnasupdate bid to match each layers MTP source (#23237)
2026-05-18 Sigbjørn Skjæretcmake : do not check for bin install dir (#23234)
2026-05-17 Gabe Goodhartfeat: Support d_conv=15 for ssm-conv.cu (#23017)
2026-05-17 Aldehir Rojascmake : fix LLAMA_BUILD_UI logic (#23190)
2026-05-17 Sigbjørn Skjæretcmake : do not install conversion script (#23204)
2026-05-17 Oliver SimonsCUDA: Continue directly including cuda/iterator (#23102)
2026-05-17 Aman Guptallama: avoid copying logits during prompt decode in...
2026-05-17 Aldehir Rojascommon : delegate assistant continuation to underlying...
2026-05-17 Jan Ekströmggml-vulkan/CMakeLists: add a check for SPIRV-Headers...
2026-05-17 Pascalvulkan: add cpy bf16 -> f32 pipelines (#22677)
2026-05-17 Jeff Bolzvulkan: Support unaligned tensors for ROPE (#22637)
2026-05-17 Aldehir Rojascommon : enable streaming JSON argument values (#23173)
2026-05-17 Jeff Bolzvulkan: fuse SSM_CONV + BIAS + SILU (#22653)
2026-05-17 Rares Vernicaserver : honor --embd-normalize CLI arg (#23125)
2026-05-17 ddh0ngram : reduce noisy logs (#23185)
2026-05-17 Juddwebui: support video files as input (#22830)
2026-05-16 Xuan-Son Nguyenserver: (router) alloc tmp buffer on heap (#23159)
2026-05-16 Pascalserver: skip device enumeration in router mode to avoid...
2026-05-16 Winston Mavulkan: removed duplicate #include <memory> in headers...
2026-05-16 Aleksander... ui: Add request timeout for MCP tool calls (#23138)
2026-05-16 Georgi Gerganovsync : ggml
2026-05-16 Georgi Gerganovggml : bump version to 0.12.0 (ggml/1494)
2026-05-16 CrispStrobemetal : tighten input-position loop in kernel_conv_tran...
2026-05-16 Steve Lhommeggml: install ggml.pc in <libdir>/pkgconfig (ggml/1480)
2026-05-16 Holger Voormannui: Correct links in `tools/ui/README.md` [no ci] ...
2026-05-16 Alessandro... vendor : update cpp-httplib to 0.45.0 (#23103)
2026-05-16 Aman Guptallama + spec: MTP Support (#22673)
2026-05-16 kubawooui: Fix handling of MCP resource template parameters...
2026-05-16 viggywebui : [ChatFormActionAdd][a11y] fix accessibility...
2026-05-16 Pascalui: untrack settings sync in props effect to prevent...
2026-05-16 Aleksander... fix: Add build step using build workflow to publish...
2026-05-16 ynankanimodel : NvFP4 quantized LM head support (#23046)
2026-05-16 Aleksander... ui: Restructure repo to use `tools/ui` folder and ...
2026-05-15 Sigbjørn Skjæretci : fix release symlinks (#23119)
2026-05-15 Omer Ozarslanwebui: Use lowercase hash for HF checksum check (#23107)
2026-05-15 Pascaltests: add BF16 non-contig coverage for MUL_MAT permuta...
2026-05-15 Julien Chaumonddocs: document `usage` object in server timings respons...
2026-05-15 Xuan-Son Nguyenmtmd: add chunks and fix preproc for qwen3a (#23073)
2026-05-15 Pascalwebui: fix theme from --webui-config-file not applied...
2026-05-15 Sigbjørn Skjæretconvert : fix Qwen3 ASR conversion (#23081)
2026-05-15 Piotr Wilkin... Refactor: convert_hf_to_gguf.py (#17114)
2026-05-15 Sigbjørn Skjæretci : fix transform of top . entry in release archive...
2026-05-15 Georgi Gerganovllama-eval : add AIME 2026 dataset support (#23058)
2026-05-15 Aman Guptareasoning-budget: clone should do a deep-copy (#23095)
2026-05-15 Pascalwebui: preserve partial response on streaming error...
2026-05-15 Sid ShaytaySupport for Codex CLI by skipping unsupported Responses...
2026-05-15 KITAITI Makotoreadme : update bindings (#23063)
2026-05-14 Pranav Dhinakarggml-hexagon: cpy: add contiguous fast-path in reshape...
2026-05-14 Johannes GäßlerHIP: RDNA3 mma FA, faster AMD transpose, tune AMD ...
2026-05-14 Zack LiCI : support IOT device (IQ9) (#22987)
2026-05-14 Reese Levineggml-webgpu: Enable NVIDIA self-hosted CI (#22976)
2026-05-14 Zheyuan Chenggml-webgpu: makes the flash attn vec path subgroup...
2026-05-14 Aleksander... fix: Propagate version tag to WebUI asset download...
2026-05-14 Aman Guptacontributing: new contributors should not submit trivia...
2026-05-14 Aleksander... webui: Move static build output from repo code to HF...
2026-05-14 Georgi Gerganovlogs : reduce (#23021)
2026-05-14 alex-spacemitggml-cpu: Add IME2 Instruction Support for the SpacemiT...
2026-05-14 Neo Zhangdocker : revert stable version of intel compute-runtime...
2026-05-14 Kabir Potdarunicode,test: add Qwen3.5 non-backtracking tokenizer...
2026-05-14 Ruben Ortlamvulkan: fix matmul integer pipeline selection (#23005)
2026-05-14 Aleksander... fix: Autoscroll detection (#23026)
2026-05-14 KatostrofikSYCL: fix multi-GPU system RAM exhaustion by using...
2026-05-13 Zheyuan Chenggml-webgpu: only use subgroup-matrix path when head...
2026-05-13 scutler-nvFix for issue #22974. Cast intermediate results to...
2026-05-13 shaofeiqiopencl: add q5_0 and q5_1 MoE for Adreno (#22985)
2026-05-13 Pascalserver, webui: accept continue_final_message flag for...
2026-05-13 lhezopencl: fix crash when warming up MoE on Adreno (#22876)
2026-05-13 Masashi Yoshimuraflush the gpu profile timestamp before the queryset...
2026-05-13 Aleksander... webui: Deduplicate model aliases in data + handle singl...
2026-05-13 Pascalwebui: preserve system message on edit cancel (#22911)
2026-05-13 Ravi Panchumarthydocs : Update OPENVINO.md (#22959)
next