ik_llama.cpp.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Expand)	Author
2023-12-03	llama : pad KV cache size (#4280)	Georgi Gerganov
2023-12-01	llama : avoid using "optional" keyword (#4283)	Georgi Gerganov
2023-12-01	llama : support optional tensors (#4283)	Georgi Gerganov
2023-12-01	llama : support attention bias on LLaMA architecture (#4283)	CausalLM
2023-12-01	llama : add Qwen support (#4281)	Shijie
2023-12-01	llama : fix integer overflow during quantization (#4284)	Georgi Gerganov
2023-12-01	ggml : add ggml_soft_max_ext (#4256)	Georgi Gerganov
2023-12-01	build : fix build info generation and cleanup Makefile (#3920)	Jared Van Bortel
2023-11-30	llama : fix alignment of general.name in print meta (#4254)	Daniel Bevenius
2023-11-30	llama : fix typical sampling (#4261)	tarcey
2023-11-28	ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offloa...	Georgi Gerganov
2023-11-25	llama : grammar `reserve` space in `decode_utf8` (#4210)	Marcus Dunn
2023-11-24	llama : set metal log callback correctly (#4204)	slaren
2023-11-24	ggml-cuda : support stablelm rope (#4156)	slaren
2023-11-23	llama : KV cache view API + better KV cache management (#4170)	Georgi Gerganov
2023-11-21	stablelm : simplify + speedup generation (#4153)	Galunid
2023-11-19	gguf-py : export chat templates (#4125)	slaren
2023-11-17	llama : increase max nodes (#4115)	slaren
2023-11-17	llama : add functions to get the model's metadata (#4013)	slaren
2023-11-17	llama : fix data units (#4101)	Georgi Gerganov
2023-11-16	Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)	Kerfuffle
2023-11-15	llama : restore prefix space in llama tokenizer (#4081)	Jared Van Bortel
2023-11-14	stablelm : StableLM support (#3586)	Galunid
2023-11-13	sync : ggml (backend v2) (#3912)	Georgi Gerganov
2023-11-13	Add ReLU and SQR CUDA ops to (partially) fix Persimmon offloading (#4041)	Kerfuffle
2023-11-10	Unbreak persimmon after #3837 (#4010)	Galunid
2023-11-07	cuda : supports running on CPU for GGML_USE_CUBLAS=ON build (#3946)	Meng Zhang
2023-11-05	llama : mark LLM_ARCH_STARCODER as full offload supported (#3945)	Meng Zhang
2023-11-03	llama : change yarn_ext_factor placeholder to -1 (#3922)	cebtenzzre
2023-11-02	llm : prevent from 1-D tensors being GPU split (#3697)	Georgi Gerganov
2023-11-01	llama : fix llama_context_default_params after #2268 (#3893)	cebtenzzre
2023-11-01	llama : implement YaRN RoPE scaling (#2268)	cebtenzzre
2023-11-01	llm : fix llm_build_kqv taking unused tensor (benign, #3837)	Georgi Gerganov
2023-11-01	llm : fix falcon norm after refactoring (#3837)	Georgi Gerganov
2023-11-01	llm : add llm_build_context (#3881)	Georgi Gerganov
2023-11-01	finetune : add -ngl parameter (#3762)	Andrew Godfrey
2023-11-01	llama : refactor graph build code (#3837)	Georgi Gerganov
2023-10-31	samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)	kalomaze
2023-10-30	ggml : move FP16 <-> FP32 code to ggml-impl.h (#3861)	Georgi Gerganov
2023-10-29	Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)	Kerfuffle
2023-10-29	llama : fix kv shift bug (#3835)	Georgi Gerganov
2023-10-29	ggml : quantization refactoring (#3833)	Georgi Gerganov
2023-10-28	llama : allow quantizing k-quants to fall back when tensor size incompatible ...	Kerfuffle
2023-10-28	starcoder : add GPU offloading (#3827)	Georgi Gerganov
2023-10-27	llama : correctly report GGUFv3 format (#3818)	cebtenzzre
2023-10-27	cuda : improve text-generation and batched decoding performance (#3776)	Georgi Gerganov
2023-10-23	llama : remove token functions with `context` args in favor of `model` (#3720)	Marcus Dunn
2023-10-22	Add test for MPT tokenization (#3728)	goerch
2023-10-22	llama : validate special token ids are in range when loading GGUF model (#3635)	Kerfuffle
2023-10-20	sampling : refactor init to use llama_sampling_params (#3696)	Georgi Gerganov