]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2025-05-13 Johannes GäßlerCUDA: FA support for Deepseek (Ampere or newer) (llama...
2025-05-13 Johannes GäßlerCUDA: fix crash on large batch size for MoE models...
2025-05-13 Radoslav Gerganovrpc : add rpc_msg_set_tensor_hash_req (llama/13353)
2025-05-13 Jeff Bolzvulkan: Allow up to 4096 elements for mul_mat_id row_id...
2025-05-13 Alberto Cabrera... sycl: addressing non-contiguous src1 mul_mats (nc and...
2025-05-08 Taylorsam : support box prompt (#1206)
2025-05-07 Georgi Gerganovsync : llama.cpp
2025-05-07 R0CKSTARcuda : remove nrows_x in mul_mat_q_process_tile (llama...
2025-05-07 Johannes GäßlerCUDA: mix virt/real CUDA archs for GGML_NATIVE=OFF...
2025-05-07 Akarshan BiswasSYCL: Disable reorder optimize by default and stop...
2025-05-07 Johannes GäßlerCUDA: fix bad asserts for partial offload (llama/13337)
2025-05-07 Johannes GäßlerCUDA: fix --split-mode row for MMQ (llama/13323)
2025-05-07 Johannes GäßlerCUDA: fix logic for clearing padding with -ngl 0 (llama...
2025-05-07 Akarshan BiswasSYCL: Disable mul_mat kernels for noncontiguous tensor...
2025-05-07 Diego Devesarpc : use backend registry, support dl backends (llama...
2025-05-07 Aaron Teoggml : activate s390x simd for Q3_K (llama/13301)
2025-05-07 Johannes GäßlerCUDA: fix race condition in MMQ stream-k fixup (llama...
2025-05-07 Johannes GäßlerCUDA: fix race condition in MMQ ids_dst (llama/13294)
2025-05-07 Jeff Bolzvulkan: Additional type support for unary, binary,...
2025-05-07 Georgi Gerganovsync : whisper.cpp
2025-05-07 Daniel Beveniuswhisper: remove MSVC warnings pragmas (whisper/3090)
2025-05-07 Jared Tweedcmake : removed stdc++fs (whisper/3097)
2025-05-02 Georgi Gerganovsync : llama.cpp upstream/0.0.2015
2025-05-02 Georgi Gerganovvulkan : fix lint (llama/0)
2025-05-02 shalinib-ibmggml : Enable MMA for BF16 in llamafile_sgemm (llama...
2025-05-02 Justin Santa... rpc : avoid uninitialized memory in serialize_tensor...
2025-05-02 Jesse Grossggml: Don't assert fail when tensor data changes (llama...
2025-05-02 Diego Devesabuild : fix build info on windows (llama/13239)
2025-05-02 Jeff Bolzvulkan: Add bfloat16 support (llama/12554)
2025-05-02 Jeff Bolzvulkan: Handle src1 batch dimension in non-contiguous...
2025-05-02 Johannes Gäßlertest: non-cont. b in test-backend-ops -o MUL_MAT (llama...
2025-05-02 Aclyvulkan : kernels for depthwise 2D convolution (CONV_2D_...
2025-05-01 Georgi Gerganovsync : whisper.cpp
2025-05-01 Daniel Beveniuswhisper : add check that target name exists (whisper...
2025-05-01 Daniel Beveniusggml : suppress Windows compiler warnings (whisper...
2025-05-01 Georgi Gerganovsync : llama.cpp
2025-05-01 Johannes GäßlerCUDA: batched+noncont MMQ, refactor bs>1 MoE code ...
2025-05-01 Jeff Bolzvulkan: use uint array index to avoid glslang bug ...
2025-05-01 shalinib-ibmggml : fix ppc64le build (llama/13176)
2025-05-01 Aaron Teofeat(ggml-cpu): enable z17 compile (llama/13182)
2025-05-01 Johannes GäßlerCUDA: fix non-cont. inputs for batched mat mul (llama...
2025-05-01 Ville Vesilehtofix(rpc): Improve input validation and error handling...
2025-05-01 Akarshan BiswasSYCL: Add all missing unary kernels (llama/13074)
2025-05-01 R0CKSTARmusa: fix typo in cc control (llama/13144)
2025-05-01 Johannes GäßlerCUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (llama...
2025-05-01 R0CKSTARmusa: fix build warning (llama/13129)
2025-05-01 SXXggml: move fp16/bf16 conversion optimizations to CPU...
2025-05-01 Xuan-Son Nguyenclip : fix pixtral on some GPU backends (llama/13097)
2025-05-01 Neo Zhang Jianyuchange the reorder tensor from init to execute OP ...
2025-05-01 Radoslav Gerganovrpc : do not wait for response when sending RPC_CMD_SET...
2025-04-30 Diego Devesaggml : fix ggml_gallocr_ptr type (#1205)
2025-04-30 Georgi Gerganovmedia : rm logos (#1203)
2025-04-29 Georgi Gerganovsync : whisper.cpp
2025-04-29 Georgi Gerganovcuda : fix unused variable compile warning (whisper/0)
2025-04-24 Georgi Gerganovopencl : remove obsolete files (skip) (#1200)
2025-04-24 Georgi Gerganovsync : llama.cpp upstream/0.0.1982
2025-04-24 Georgi Gerganovmetal : add memory pool for temp allocs (llama/12850)
2025-04-24 lhezopencl: split ggml-opencl.cl into multiple files and...
2025-04-24 Georgi Gerganovggml : fix trailing whitespaces (llama/0)
2025-04-24 Johannes GäßlerCUDA: use switch statements in constexpr functions...
2025-04-24 Georgi Gerganovmetal : fix floating-point range of attention scores...
2025-04-24 Evevulkan: matmul gcn tuning (llama/13016)
2025-04-24 Johannes GäßlerCUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (llama...
2025-04-24 Diego Devesaggml : add SSE 4.2 and x64 base variant for CPUs withou...
2025-04-24 Akarshan BiswasSYCL: Add non-contiguous support in ROPE (llama/12993)
2025-04-24 Jeff Bolzvulkan: support noncontiguous rms_norm (llama/13031)
2025-04-24 Jeffrey Morganmetal: add neg operator (llama/13029)
2025-04-24 Akarshan BiswasSYCL: Refactor and enable FP16 in binary broadcast...
2025-04-24 Radoslav Gerganovrpc : add RPC_CMD_HELLO (llama/12955)
2025-04-24 Georgi Gerganovgraph : make FA compatible with MLA + add initial Metal...
2025-04-24 Alan Grayggml: Re-enable CUDA graphs in presence of CONT and...
2025-04-24 hipuddingCANN: Add support for async operator submission (llama...
2025-04-24 kimminsuopencl: fix incorrect local_size index in profiling...
2025-04-24 Jeff Bolzvulkan: enable coopmat2 FA gqa and split_k optimization...
2025-04-24 Chenguang LiCANN: Add 310P operator support check (llama/12962)
2025-04-24 Georgi Gerganovmetal : add FA-vec kernels for head size 96 (llama...
2025-04-24 hipuddingCANN: Add x86 build ci (llama/12950)
2025-04-24 David HuangCUDA/HIP: Share the same unified memory allocation...
2025-04-24 Akarshan BiswasSYCL: Add ROPE vision kernel (llama/12887)
2025-04-24 Srihari-mcwggml : Add AVX512 implementation of GEMM - Q4_Kx8 ...
2025-04-24 Chenguang LiCANN: Opt ROPE optimization (llama/12865)
2025-04-24 Xinpeng DouCANN: Optimize CANN buffer pool memory management ...
2025-04-24 Akarshan BiswasSYCL: Fix im2col (llama/12910)
2025-04-24 Radoslav Gerganovrpc : use ggml_context_ptr (llama/12938)
2025-04-24 Georgi Gerganovscripts : update sync-llama-am.sh
2025-04-19 Leonard Mosescutests : Fix a few small Windows / MSVC build issues...
2025-04-17 Aclyggml : Depthwise 2D convolution (#1152)
2025-04-14 Georgi Gerganovsync : llama.cpp
2025-04-14 SXXggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly...
2025-04-14 Alan Grayggml: disable CUDA graphs for unsupported DUP and CONT...
2025-04-14 Jeff Bolzvulkan: use aligned loads for flash attention mask...
2025-04-14 Ewan Crawfordsycl: Support sycl_ext_oneapi_limited_graph (llama...
2025-04-14 Akarshan BiswasSYCL: Add fp16 type support to unary op kernels (llama...
2025-04-14 Aaron Teoggml: fix compilation error s390x (llama/12848)
2025-04-14 Georgi Gerganovtests : fix init order (llama/0)
2025-04-11 cmdr2cpu: fix cpu backend's supports-op for GET_ROWS_BACK...
2025-04-10 Georgi Gerganovsync : fix (skip) (#0)
2025-04-10 Georgi Gerganovsync : llama.cpp
2025-04-10 Chenguang LiCANN: Support more ops (llama/12841)
2025-04-10 Prajwal B MehendarkarFixes #12823 (llama/12830)
next