aboutsummaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2023-07-24Fix scalar version of Q5_K when QK_K = 64 (#2362)Kawrakow
2023-07-23llama : add grammar-based sampling (#1773)Evan Jones
2023-07-24Some more Q4_K and Q5_K speedup on CUDA (#2346)Kawrakow
2023-07-23Add gqa parameter support to the server (#2351)IgnacioFDM
2023-07-23Fix __dp4a documentation (#2348)Johannes Gäßler
2023-07-23common : n_threads == -1 uses std::thread::hardware_concurrency() (#2347)wzy
2023-07-23fix n_tasks (#2342)slaren
2023-07-23ggml: move op parameters from tensors to ggml_tensor::op_params (#2333)slaren
2023-07-23llama : grouped-query attention + LLaMAv2 70B support (#2276)Georgi Gerganov
2023-07-23llama : print help to stdout (#2338)maddes8cht
2023-07-23flake : support `nix build '.#opencl'` (#2337)wzy
2023-07-23llama : print max tensor size to stderr (#2336)Christian Demsar
2023-07-23make : fix CLBLAST compile support in FreeBSD (#2331)Jose Maldonado
2023-07-23examples : simplify vim plugin (#2327)AustinMroz
2023-07-23metal : support bcast add & dup & cont op (#2323)Jiahao Li
2023-07-23Speed up Q4_K (#2322)Kawrakow
2023-07-22CUDA: Fixed 7b q3_K_S with mul_mat_vec_q (#2313)Johannes Gäßler
2023-07-22llama : optimize memory buffers (#2325)Georgi Gerganov
2023-07-22Perplexity: Compute scores correlated to HellaSwag (#2312)klosax
2023-07-22examples : basic VIM pluginwhoreson
2023-07-22ci : fix argsGeorgi Gerganov
2023-07-22ci : add 7B CUDA tests (#2319)Georgi Gerganov
2023-07-21examples : add easy python script to create quantized (k-bit support) GGML mo...Richard Roberson
2023-07-21Custom RoPE + bettter memory management for CUDA (#2295)Kawrakow
2023-07-21Faster Q3_K implementation on Metal (#2307)Kawrakow
2023-07-21ggml : fix the rope fix (513f8619535a64fa9ace808cdcbcf66211535f5c)Georgi Gerganov
2023-07-21examples : fix typo in minigpt4.py (#2298)Ikko Eltociear Ashimine
2023-07-21ggml : fix rope args order + assert (#2054)Georgi Gerganov
2023-07-21gitignore : fix final newlineGeorgi Gerganov
2023-07-21llama : remove cfg smooth factor as it is only a reparameterization of the gu...Guillaume "Vermeille" Sanchez
2023-07-21gitignore : changes for Poetry users + chat examples (#2284)Jose Maldonado
2023-07-21make : fix indentationGeorgi Gerganov
2023-07-21ci : fix MNT realpath usage (#2250)Georgi Gerganov
2023-07-21make : support customized LLAMA_CUDA_NVCC and LLAMA_CUDA_CCBIN (#2275)Sky Yan
2023-07-21flake : remove intel mkl from flake.nix due to missing files (#2277)wzy
2023-07-21llama : make tensor_split ptr instead of array (#2272)Georgi Gerganov
2023-07-21make : add new target for test binaries (#2244)Jiří Podivín
2023-07-21MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)Hatsune Miku
2023-07-21Faster Q2_K on Metal (#2297)Kawrakow
2023-07-21make : fix embdinput library and server examples building on MSYS2 (#2235)Przemysław Pawełczyk
2023-07-20Faster Q5_K and Q6_K on Metal (#2294)Kawrakow
2023-07-20Faster Q4_K on Metal (#2290)Kawrakow
2023-07-20llama : fix regression from #2000 - could not load no-mmap modelsGeorgi Gerganov
2023-07-20metal: minor q4 optimization and reduce code size (#2248)Shouzheng Liu
2023-07-19llama : extend API to get max devices at runtime (#2253)Rinne
2023-07-19flake : update flake.nix (#2270)wzy
2023-07-19cmake : install targets (#2256)wzy
2023-07-18ci : integrate with ggml-org/ci (#2250)Georgi Gerganov
2023-07-18llama : shorten quantization descriptionsGeorgi Gerganov
2023-07-17Support dup & cont ops on CUDA (#2242)Jiahao Li
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-18 17:25:58 +0000