]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2024-03-10 Georgi Gerganovsync : whisper.cpp
2024-03-10 Josh Bleecher... whisper : document whisper_batch.n_seq_id (whisper...
2024-03-10 Josh Bleecher... whisper : improve beam search candidate diversity ...
2024-03-10 Josh Bleecher... whisper : make beam candidate sort more stable (whisper...
2024-03-10 Georgi Gerganovggml : try fix 32-bit arm compat (whisper/1938)
2024-03-08 Georgi Gerganovsync : whisper.cpp
2024-03-08 F1L1Pexamples : Auto lowercase language parameter in main...
2024-03-08 zhouwgwhisper : fix typo (whisper/1925)
2024-03-08 Georgi Gerganovsync : llama.cpp
2024-03-08 Neo Zhang JianyuRevert "[SYCL] fix error when set main gpu to non-zero...
2024-03-08 Neo Zhang Jianyufix error when set main gpu to non-zero (llama/5901)
2024-03-08 Jared Van Bortelggml : use SYS_get_cpu if SYS_getcpu is not defined...
2024-03-08 bobqianicggml : use `uint8x16_t` return type for `ggml_vqtbl1q_u...
2024-03-08 Neo Zhang Jianyuadd wait() to make code stable (llama/5895)
2024-03-08 Jared Van Bortelquants : use MM256_SET_M128I consistently to fix gcc...
2024-03-08 0cc4mVulkan Improvements (llama/5835)
2024-03-08 Neo Zhang Jianyufix mul_mat fault in CI/unit-test (llama/5862)
2024-03-08 Georgi Gerganovggml : fix unknown status (llama/0)
2024-03-07 slarenmagika : fix ggml_backend_graph_compute status check...
2024-03-05 Georgi Gerganovwhisper : fix compute helper return (#750)
2024-03-04 Michael Podvitskiyggml : introduce ggml_status (#750)
2024-03-04 Georgi Gerganovsync : llama.cpp
2024-03-04 slarencuda : fix data race in soft max (llama/5853)
2024-03-04 Georgi Gerganovggml : fix IQ3_S AVX implementation (llama/5834)
2024-03-04 Kawrakowggml : IQ3_S improvements (llama/5829)
2024-03-04 Neo Zhang JianyuSupport multiple GPUs (split mode) on SYCL backend...
2024-03-04 ddpasaggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was...
2024-03-04 AidanBeltonSUse batched mul_mat pathway (llama/5591)
2024-03-04 Evemake portability_enumeration_ext apple only (llama...
2024-03-03 leejetadd some new ops, fix some operators and add batch...
2024-02-28 Steward Garciaggml : add simple example (#713)
2024-02-28 Georgi Gerganovsync : whisper.cpp
2024-02-28 Tamotsu Takahashitalk, talk-llama : pass text_to_speak as a file (whispe...
2024-02-28 Abhilash Majumderwhisper : add SYCL support (whisper/1863)
2024-02-28 Georgi Gerganovsync : llama.cpp (#0)
2024-02-28 Kawrakowggml : make i-quants work with super-blocks of 64 ...
2024-02-28 KawrakowAttempt to fix android build (llama/5752)
2024-02-28 KawrakowIQ4_XS: a 4.25 bpw quantization (llama/5747)
2024-02-28 Engininja2cuda : replace remaining shfl_xor with calls to warp_re...
2024-02-28 Engininja2ggml-quants : fix avx2 iq1_s vec_dot when compiled...
2024-02-28 KawrakowAdding IQ2_S and IQ2_M to complete coverage of the...
2024-02-28 Johannes GäßlerCUDA: fix DEBUG_CUDA_MALLOC (llama/5729)
2024-02-28 AidanBeltonSAdd support for soft_max ALiBi (llama/5639)
2024-02-28 Radosław Grytaggml-quants : provide ggml_vqtbl1q_u8 for 64bit compati...
2024-02-25 slarenadd google magika inference example (#748)
2024-02-25 Georgi Gerganovsync : llama.cpp (#0)
2024-02-25 Georgi Gerganovcode : normalize enum names (llama/5697)
2024-02-25 KawrakowIQ3_S: a much better alternative to Q3_K (llama/5676)
2024-02-25 Ondřej Čertíkmnist : fix the emcc command to compile correctly ...
2024-02-24 UEXTM.comIntroduce backend GUIDs (#743)
2024-02-22 Georgi Gerganovsync : llama.cpp
2024-02-22 Georgi Gerganovggml : always define ggml_fp16_t as uint16_t (llama...
2024-02-22 Georgi Gerganovsync : whisper.cpp
2024-02-22 Georgi Gerganovggml : 32-bit arm compat (whisper/1891)
2024-02-22 Davidson Francismain : fix file existence check in main.cpp (whisper...
2024-02-21 Georgi Gerganovsync : llama.cpp (#0)
2024-02-21 Meng, Hengyuconext add name (llama/5624)
2024-02-21 AidanBeltonSUpdate ggml_sycl_op_mul_mat_vec_q (llama/5502)
2024-02-21 0cc4mRefactor validation and enumeration platform checks...
2024-02-21 0cc4mAdd check for VK_KHR_portability_enumeration for Molten...
2024-02-21 Mathijs de... Add preprocessor checks for Apple devices.
2024-02-21 Mathijs de... Resolve ErrorIncompatibleDriver with Vulkan on MacOS.
2024-02-21 Mathijs de... Allow for Vulkan build with Accelerate.
2024-02-21 slarencuda : ignore peer access already enabled errors (llama...
2024-02-21 Siddharth Ramakrishnanggml : compute forward no longer pass src tensors ...
2024-02-20 bssrdfggml : fix conv_2d batch mode (#737)
2024-02-19 Georgi Gerganovsync : whisper.cpp
2024-02-19 Georgi Gerganovbuild : update CBLAS flags + fix unused var warning...
2024-02-19 Davidson Francismain : check if input files exist before proceeding...
2024-02-19 Felixexamples : clean up common code (whisper/1871)
2024-02-19 Georgi Gerganovwhisper : fix external encoder (whisper/1860)
2024-02-19 Georgi Gerganovggml : resolve merge conflicts (#0)
2024-02-19 Georgi Gerganovcommon : add IQ1_S (#0)
2024-02-19 Georgi Gerganovsync : llama.cpp
2024-02-19 Georgi Gerganovci : enable -Werror for CUDA builds (llama/5579)
2024-02-19 slarencuda, metal : fix nans in soft_max (llama/5574)
2024-02-19 bmwlggml : android and old glibc NUMA incompatibility bugfi...
2024-02-19 Georgi Gerganovggml : restore vec dot stride arg names (llama/5453)
2024-02-19 Georgi Gerganovci : fix wikitext url + compile warnings (llama/5569)
2024-02-19 Georgi Gerganovmetal : fix unused warnings (llama/0)
2024-02-19 Herman Semenovggml, common, examples, tests : fixed type arguments...
2024-02-19 Kawrakow1.5 bit quantization (llama/5453)
2024-02-19 Georgi Gerganovggml : add ALiBi support for ggml_soft_max_ext (llama...
2024-02-19 Georgi Gerganovsync : llama.cpp
2024-02-19 Ananta Bastolaci : add an option to fail on compile warning (llama...
2024-02-19 Georgi Gerganovcmake : fix VULKAN and ROCm builds (llama/5525)
2024-02-19 bmwlggml : add numa options (llama/5377)
2024-02-19 slarencuda : print message when initialization fails (llama...
2024-02-19 Neuman Vongvulkan: Find optimal memory type but with fallback...
2024-02-19 ATEarly return for zero size calls to get_tensor. (llama...
2024-02-19 Georgi Gerganovtests : disable moe test (llama/5473)
2024-02-19 Kawrakowggml-quants : fix compiler warnings (shadow variable...
2024-02-19 Abhilash Majumderggml-sycl: Replace 3d ops with macro (llama/5458)
2024-02-19 Georgi Gerganovcmake : update CBLAS build flags (#0)
2024-02-12 slarenggml-alloc : allocate all leafs as if they were inputs...
2024-02-12 Georgi Gerganovsync : whisper.cpp
2024-02-12 dscripkaexamples : added audio_ctx argument to main and server...
2024-02-12 Didzis Goskometal : option to embed MSL source into compiled binary...
2024-02-12 Georgi Gerganovexamples : initialize context params properly (whisper...
2024-02-12 Georgi Gerganovsync : llama.cpp
next