]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-04-28 Georgi Gerganovcommon : fix noreturn compile warning (#13151)
2025-04-28 Xuan-Son Nguyenllama-chat : fix typo GML --> GLM (#13143)
2025-04-28 R0CKSTARmusa: fix typo in cc control (#13144)
2025-04-28 Johannes GäßlerCUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (...
2025-04-28 Xuan-Son Nguyenarg : fix unused variable (#13142)
2025-04-27 4onenllama-bench : Add `--override-tensors` arg (#12922)
2025-04-27 matteollama-chat : fix wrong template in GLM4-0414 (#13140)
2025-04-27 R0CKSTARmusa: fix build warning (#13129)
2025-04-27 LostRuins ConcedoFixes Qwen2.5VL segfault during inference with https...
2025-04-27 HimariOclip : Add Qwen2.5VL support (#12402)
2025-04-26 Xuan-Son Nguyencommon : add common_remote_get_content (#13123)
2025-04-26 Xuan-Son Nguyenclip : improve projector naming (#13118)
2025-04-26 SXXggml: move fp16/bf16 conversion optimizations to CPU...
2025-04-26 frobgrammar : handle maxItems == 0 in JSON schema (#13117)
2025-04-25 Diego Devesallama : fix K-shift with quantized K and BLAS backend...
2025-04-25 CityForce FP32 compute in GLM4 FFN Down (#13101)
2025-04-25 Xuan-Son Nguyenclip : fix pixtral on some GPU backends (#13097)
2025-04-25 Neo Zhang Jianyuchange the reorder tensor from init to execute OP ...
2025-04-25 Radoslav Gerganovrpc : do not wait for response when sending RPC_CMD_SET...
2025-04-24 Xuan-Son Nguyenclip : remove boi/eoi embeddings for GLM-edge model...
2025-04-24 Georgi Gerganovembeddings : fix batch sizes (#13076) upstream/0.0.5185
2025-04-24 Georgi Gerganovggml : fix trailing whitespaces (#0)
2025-04-24 Georgi Gerganovsync : ggml
2025-04-24 Aclyggml : Depthwise 2D convolution (ggml/1152)
2025-04-24 Johannes GäßlerCUDA: use switch statements in constexpr functions...
2025-04-24 Georgi Gerganovcmake : do not include ./src as public for libllama...
2025-04-24 Georgi Gerganovclang-tidy : disable warning about missing math parenth...
2025-04-24 Xuan-Son Nguyenarg : add --no-mmproj-offload (#13093)
2025-04-24 Xuan-Son Nguyenarg : clean up handling --mmproj with -hf (#13082)
2025-04-24 Georgi Gerganovmetal : fix floating-point range of attention scores...
2025-04-24 Evevulkan: matmul gcn tuning (#13016)
2025-04-23 pl752llama-mtmd-cli: Sigint rework in mtmd vision example...
2025-04-23 Xuan-Son Nguyenmtmd : Support Pixtral 12B (#13065)
2025-04-23 piDackconvert : Append mult-eos,half-rope,bos to GLM4-0414...
2025-04-23 Radoslav Gerganovrpc : add command line option for number of threads...
2025-04-22 Johannes GäßlerCUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (#13014)
2025-04-22 Xuan-Son Nguyenmtmd : support SmolVLM (version 1 and 2) (#13050)
2025-04-22 Georgi Gerganovsecurity : add note about RPC and server functionality...
2025-04-22 Georgi Gerganovmetal : add memory pool for temp allocs (#12850)
2025-04-22 Xuan-Son Nguyenllava : update documentations (#13055)
2025-04-21 Diego Devesaggml : add SSE 4.2 and x64 base variant for CPUs withou...
2025-04-21 Akarshan BiswasSYCL: Add non-contiguous support in ROPE (#12993)
2025-04-21 Xuan-Son Nguyenmtmd : merge llava, gemma3 and minicpmv CLI into single...
2025-04-20 Xuan-Son Nguyenconvert : experimental support for `--mmproj` flag...
2025-04-20 Jeffrey Morganllava: fix errors in clip.h on certain compilers (...
2025-04-20 Jeff Bolzvulkan: support noncontiguous rms_norm (#13031)
2025-04-20 Jeffrey Morganmetal: add neg operator (#13029)
2025-04-19 bandotiDisable CI cross-compile builds (#13022)
2025-04-19 Sigbjørn Skjæretgguf-py : fix upload python package workflow (#13020) gguf-v0.16.2
2025-04-19 Xuan-Son Nguyenclip : refactor, add `image_manipulation` and `llava_uh...
2025-04-18 Daniel Tangmain : Fix Ctrl+D/newline handling (#12951)
2025-04-18 Chris Thompsongguf-py : GGUF Editor GUI - Python + Qt6 (#12930) gguf-v0.16.1
2025-04-18 Xuan-Son Nguyenserver : use std::move whenever possible (#12936)
2025-04-18 Akarshan BiswasSYCL: Refactor and enable FP16 in binary broadcast...
2025-04-18 Xuan-Son Nguyenmtmd : add methods to access `mtmd_image_tokens` (...
2025-04-18 Radoslav Gerganovrpc : add RPC_CMD_HELLO (#12955)
2025-04-17 Georgi Gerganovgraph : make FA compatible with MLA + add initial Metal...
2025-04-17 Alan Grayggml: Re-enable CUDA graphs in presence of CONT and...
2025-04-17 hipuddingCANN: Add support for async operator submission (#12864)
2025-04-17 Mikko Juolallama : recognize IBM Granite 3.3 FIM tokens (#12988)
2025-04-16 kimminsuopencl: fix incorrect local_size index in profiling...
2025-04-16 Jeff Bolzvulkan: enable coopmat2 FA gqa and split_k optimization...
2025-04-16 Chenguang LiCANN: Add 310P operator support check (#12962)
2025-04-15 lhezopencl: split `ggml-opencl.cl` into multiple files...
2025-04-15 Georgi Gerganovmetal : add FA-vec kernels for head size 96 (#12952)
2025-04-15 hipuddingCANN: Add x86 build ci (#12950)
2025-04-15 David HuangCUDA/HIP: Share the same unified memory allocation...
2025-04-15 Akarshan BiswasSYCL: Add ROPE vision kernel (#12887)
2025-04-15 Juk Armstrongllama : DeepSeek V2/V3 MLA implementation (#12801)
2025-04-15 Srihari-mcwggml : Add AVX512 implementation of GEMM - Q4_Kx8 ...
2025-04-15 Chenguang LiCANN: Opt ROPE optimization (#12865)
2025-04-15 Xinpeng DouCANN: Optimize CANN buffer pool memory management ...
2025-04-14 RussyydsAdd performance print for gemma3 in example (#12929)
2025-04-14 Akarshan BiswasSYCL: Fix im2col (#12910)
2025-04-14 Radoslav Gerganovrpc : use ggml_context_ptr (#12938)
2025-04-14 Neo Zhang Jianyudsiable curl lib check, this action is missed by commit...
2025-04-14 Georgi Gerganovsync : ggml
2025-04-14 cmdr2cpu: fix cpu backend's supports-op for GET_ROWS_BACK...
2025-04-14 SXXggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly...
2025-04-13 Alan Grayggml: disable CUDA graphs for unsupported DUP and CONT...
2025-04-13 Ed Addarioquantize: Handle user-defined quantization levels for...
2025-04-12 Prajwal B Mehendarkarcommon : Define cache directory on AIX (#12915)
2025-04-12 Jeff Bolzvulkan: use aligned loads for flash attention mask...
2025-04-12 Matt Claytonllava: Fix cpu-only clip image encoding sefault (#12907)
2025-04-11 Georgi Gerganovserver : add VSCode's Github Copilot Chat support ...
2025-04-11 yuri@FreeBSDrpc : Set cache directory in rpc-server.cpp on FreeBSD...
2025-04-11 Olivier Chafik`tool-call`: fix non-tool-calling grammar crashes w...
2025-04-11 yuri@FreeBSDcommon : Define cache directory on FreeBSD (#12892)
2025-04-11 Ewan Crawfordsycl: Support sycl_ext_oneapi_limited_graph (#12873)
2025-04-11 tastelikefeetcontrib: support modelscope community (#12664)
2025-04-11 Yuxuan Zhangllama-model : add Glm4Model implementation for GLM...
2025-04-11 Xuan-Son Nguyenclip : use smart pointer (⚠️ breaking change) (#12869)
2025-04-11 Akarshan BiswasSYCL: Add fp16 type support to unary op kernels (#12788)
2025-04-11 Daniel Hanconvert : Llama4 RoPE fix (#12889)
2025-04-11 R0CKSTARci : Replace freediskspace to free_disk_space in docker...
2025-04-11 Daniel Beveniusxcf : add check for visionos build version (#12854)
2025-04-11 Xuan-Son Nguyenconvert : proper tensor name mapping for llama4 (#12870)
2025-04-11 Xuan-Son Nguyenllama : correct rms norm for llama 4 (#12882)
2025-04-11 Aaron Teoggml: fix compilation error s390x (#12848)
2025-04-10 Georgi Gerganovsync : ggml
next