]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-05-07 Ycroscommon : Add a warning when we can't match samplers...
2025-05-07 R0CKSTARcuda : remove nrows_x in mul_mat_q_process_tile (#13325)
2025-05-07 Georgi Gerganovexamples : remove infill (#13283)
2025-05-07 piDackllama : support tie embedding for chatglm models (...
2025-05-06 Johannes GäßlerCUDA: mix virt/real CUDA archs for GGML_NATIVE=OFF...
2025-05-06 Xuan-Son Nguyenclip : refactor graph builder (#13321)
2025-05-06 DocShotgunsampling : make top_n_sigma no-op at <=0 or a single...
2025-05-06 oobaboogasampling : don't consider -infinity values in top_n_sig...
2025-05-06 Diego Devesacmake : remove arm64 msvc presets (#13342)
2025-05-06 Akarshan BiswasSYCL: Disable reorder optimize by default and stop...
2025-05-06 Xuan-Son Nguyenllama : fix build_ffn without gate (#13336)
2025-05-06 Johannes GäßlerCUDA: fix bad asserts for partial offload (#13337)
2025-05-06 Sigbjørn Skjæretconvert : qwen2/3moe : set yarn metadata if present...
2025-05-06 Johannes GäßlerCUDA: fix --split-mode row for MMQ (#13323)
2025-05-06 compiladegguf-py : avoid requiring pyside6 for other scripts...
2025-05-05 Johannes GäßlerCUDA: fix logic for clearing padding with -ngl 0 (...
2025-05-05 oobaboogasampling : Integrate Top-nσ into main sampling chain...
2025-05-05 igardevserver : Webui - change setText command from parent...
2025-05-05 Xuan-Son Nguyenmtmd : rename llava directory to mtmd (#13311)
2025-05-05 Xuan-Son Nguyenclip : fix confused naming ffn_up and ffn_down (#13290)
2025-05-05 Sigbjørn Skjæretconvert : bailingmoe : set yarn metadata if present...
2025-05-05 Akarshan BiswasSYCL: Disable mul_mat kernels for noncontiguous tensor...
2025-05-04 Xuan-Son Nguyenmtmd : add C public API (#13184)
2025-05-04 Diego Devesarpc : use backend registry, support dl backends (#13304)
2025-05-04 Aaron Teoggml : activate s390x simd for Q3_K (#13301)
2025-05-04 Diego Devesallava/mtmd : fixes to fully support dl backends (#13303)
2025-05-04 Diego Devesallama : build windows releases with dl backends (#13220)
2025-05-04 Johannes GäßlerCUDA: fix race condition in MMQ stream-k fixup (#13299)
2025-05-04 Johannes GäßlerCUDA: fix race condition in MMQ ids_dst (#13294)
2025-05-04 Jeff Bolzvulkan: Additional type support for unary, binary,...
2025-05-03 Johannes Gäßlerimatrix: fix oob writes if src1 is not contiguous ...
2025-05-03 Xuan-Son Nguyenclip : revert the change of BOI/EOI token for GLM-edge...
2025-05-03 ymckillama : Llama-3_1-Nemotron-Ultra-253B-v1 support (...
2025-05-02 Diego Devesallama : move end-user examples to tools directory ...
2025-05-02 Georgi Gerganovsync : ggml (#13268)
2025-05-02 Georgi Gerganovcontext : fix reorder logic (#13267)
2025-05-02 shalinib-ibmggml : Enable MMA for BF16 in llamafile_sgemm (#13148)
2025-05-02 Jared Van Bortelllama-model : support Qwen2 embedding models and poolin...
2025-05-02 Jared Van Bortelconvert : use correct context length for nomic-embed...
2025-05-02 Xuan-Son Nguyenconvert : converting mmproj for Qwen2/2.5VL from conver...
2025-05-02 Georgi Gerganovkv-cache : separate recurrent vs non-recurrent impl...
2025-05-02 Sigbjørn Skjæretllama : orion rope type is neox (#13261)
2025-05-02 Sigbjørn Skjæretllama : plamo rope type is neox (#13260)
2025-05-02 piDackllama-chat : reset glmedge chat template (#13253)
2025-05-02 Shakil Ahmedmtmd-cli : fix out_of_range when input image path is...
2025-05-02 Georgi Gerganovserver : add cache reuse card link to help (#13230)
2025-05-02 Xuan-Son Nguyenconvert : explicitly disable trust_remote_code for...
2025-05-01 bandotici: fix cross-compile sync issues (#12804)
2025-05-01 Justin Santa... rpc : avoid uninitialized memory in serialize_tensor...
2025-05-01 Jesse Grossggml: Don't assert fail when tensor data changes (...
2025-05-01 Diego Devesabuild : fix build info on windows (#13239)
2025-05-01 Loïc Carrèreclip : (minicpmv) Re-enable upscaling of images smaller...
2025-05-01 matteollama-chat : update GLM4 chat template (#13238)
2025-05-01 Jeff Bolzvulkan: Add bfloat16 support (#12554)
2025-05-01 Jeff Bolzvulkan: Handle src1 batch dimension in non-contiguous...
2025-05-01 Johannes Gäßlertest: non-cont. b in test-backend-ops -o MUL_MAT (...
2025-05-01 Georgi Gerganovsync : ggml
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 Xuan-Son Nguyenmtmd : add **vision** support for Mistral Small 3.1...
2025-05-01 Xuan-Son Nguyenarg : remove CURLINFO_EFFECTIVE_METHOD (#13228)
2025-05-01 Jared Van Bortelllama-model : fix the reported size class for nomic...
2025-05-01 Georgi Gerganovsync : ggml
2025-05-01 Diego Devesaggml : fix ggml_gallocr_ptr type (ggml/1205)
2025-05-01 Georgi Gerganovcuda : fix unused variable compile warning (whisper/0)
2025-04-30 Johannes GäßlerCUDA: batched+noncont MMQ, refactor bs>1 MoE code ...
2025-04-30 Xuan-Son Nguyenarg : -hf do not fail if url mismatch (#13219)
2025-04-30 ddh0fix typo: `n_ctx_pre_seq` -> `n_ctx_per_seq` (#13221)
2025-04-30 Xuan-Son Nguyenconvert : improve model arch handling (#13122)
2025-04-30 Tatsuya Tanakallava : remove duplicate include (#13207)
2025-04-30 Olivier Chafikcommon : add -jf / --json-schema-file flag (#12011)
2025-04-30 Jeff Bolzvulkan: use uint array index to avoid glslang bug ...
2025-04-30 shalinib-ibmggml : fix ppc64le build (#13176)
2025-04-30 Xuan-Son Nguyenconvert : correct typo image_mean --> image_std (#13208)
2025-04-30 Aaron Teofeat(ggml-cpu): enable z17 compile (#13182)
2025-04-30 Xuan-Son Nguyenarg : allow using -hf offline (#13202)
2025-04-30 Xuan-Son Nguyendocker : do not build tests (#13204)
2025-04-30 xiaofeirpc : fix cache directory initialization (#13188)
2025-04-29 Johannes Gäßlerscripts: n_depth for compare-llama-bench [no ci] (...
2025-04-29 matteoserver : Prefilling assistant message in openai compati...
2025-04-29 Georgi Gerganovsampling : when top-k <= 0 -> noop (#13173)
2025-04-29 Alberto Cabrera... llama-bench: fixed size of fields to correctly map...
2025-04-29 Johannes GäßlerCUDA: fix non-cont. inputs for batched mat mul (#13155)
2025-04-29 Sigbjørn Skjæretllama : llm_type order by size (#13177)
2025-04-29 Xuan-Son Nguyenmtmd : add qwen2vl and qwen2.5vl (#13141)
2025-04-29 Sigbjørn Skjæretllama : set qwen3 model type sizes (#13175)
2025-04-29 Xuan-Son Nguyenllama-graph : fix text position for mrope (#13159)
2025-04-28 ATmodel : Nomic Embed Text V2 with Mixture-of-Experts...
2025-04-28 Xuan-Son Nguyenclip : fix model size display (#13153)
2025-04-28 Ville Vesilehtofix(rpc): Improve input validation and error handling...
2025-04-28 Vishal Agarwalllama-bench: add `-d` depth arg (#13096)
2025-04-28 Xuan-Son Nguyenmtmd : fix glm-edge redundant token count (#13139)
2025-04-28 pockers21context : do not clear output buffer on reserve (#13152)
2025-04-28 Xuan-Son Nguyenllama : (mrope) allow using normal 1D position for...
2025-04-28 Xuan-Son Nguyenclip : refactor set input for cgraph + fix qwen2.5vl...
2025-04-28 Akarshan BiswasSYCL: Add all missing unary kernels (#13074)
2025-04-28 Georgi Gerganovreadme : update hot topics (#13150)
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)
next