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

Age	Commit message (Expand)	Author
2024-02-18	common : fix ub (#5530)	Georgi Gerganov
2024-02-18	ggml, common, examples, tests : fixed type arguments in printf (#5528)	Herman Semenov
2024-02-16	server : add "samplers" param to control the samplers order (#5494)	Alexey Parfenov
2024-02-16	ggml : add numa options (#5377)	bmwl
2024-02-11	common : use enums for sampler types (#5418)	Alexey Parfenov
2024-02-11	ggml : add mmla kernels for quantized GEMM (#4966)	snadampal
2024-02-07	Basic Vulkan Multi-GPU implementation (#5321)	0cc4m
2024-02-05	common : add dynamic temperature parameters to main example cli (#5295)	l3utterfly
2024-02-03	refactor : switch to emplace_back to avoid extra object (#5291)	Michael Klimenko
2024-01-31	llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)	Georgi Gerganov
2024-01-31	Vulkan Fixes (#5223)	0cc4m
2024-01-30	kompute : llama-bench support and ggml_cpu_has_kompute() (#5226)	Jared Van Bortel
2024-01-28	ggml : add unified SYCL backend for Intel GPUs (#2690)	Abhilash Majumder
2024-01-23	minor : clean-up some warnings and style (#5094)	Georgi Gerganov
2024-01-22	KL-divergence (#5076)	Kawrakow
2024-01-21	Add ability to evauate multiple choice tasks (#5047)	Kawrakow
2024-01-18	Add Winogrande evaluation (#5015)	Kawrakow
2024-01-16	speculative : threading options (#4959)	stduhpf
2024-01-13	main : add parameter --no-display-prompt (#4541)	Yann Follet
2024-01-12	llama : ggml-backend integration (#4766)	slaren
2024-01-12	common : streamline the formatting of help (#4890)	howlger
2024-01-12	llama : fix llm_build_k_shift to use correct n_rot (#4889)	Georgi Gerganov
2024-01-11	main : better name for variable n_print (#4874)	Georgi Gerganov
2024-01-11	main : disable token count by default (#4874)	Georgi Gerganov
2024-01-11	main : print total token count and tokens consumed so far (#4874)	pudepiedj
2024-01-08	common : fix the short form of `--grp-attn-w`, not `-gat` (#4825)	howlger
2024-01-08	main : add self-extend support (#4815)	Georgi Gerganov
2023-12-30	ggml : add ggml_cpu_has_avx_vnni() (#4589)	automaticcat
2023-12-21	common : remove incorrect --model-draft default (#4568)	Jared Van Bortel
2023-12-13	common : add `--version` option to show build info in CLI (#4433)	Siwen Yu
2023-12-07	llama : per-layer KV cache + quantum K cache (#4309)	Georgi Gerganov
2023-12-05	llama : allow overriding GGUF metadata when loading model (#4092)	Kerfuffle
2023-12-05	sampling : custom samplers order (#4285)	MaggotHATE
2023-11-23	llama : KV cache view API + better KV cache management (#4170)	Georgi Gerganov
2023-11-20	main : Add ChatML functionality to main example (#4046)	Seb C
2023-11-19	common : comma should be semicolon (#4137)	kchro3
2023-11-17	common : improve yaml log escaping (#4080)	Jannis Schönleber
2023-11-16	Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)	Kerfuffle
2023-11-05	ggml-cuda : fix f16 mul mat (#3961)	slaren
2023-11-05	Allow common process_escapes to handle \x sequences (#3928)	Kerfuffle
2023-11-03	speculative : change default p_accept to 0.5 + CLI args (#3919)	Georgi Gerganov
2023-11-02	build : link against build info instead of compiling against it (#3879)	cebtenzzre
2023-11-01	llama : implement YaRN RoPE scaling (#2268)	cebtenzzre
2023-11-01	common : minor (#3715)	Georgi Gerganov
2023-11-01	common : allow caller to handle help/argument exceptions (#3715)	bandoti
2023-10-31	samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)	kalomaze
2023-10-29	Extend llama_kv_cache_seq_rm to allow matching any sequence (#3843)	Kerfuffle
2023-10-28	llama : add option for greedy sampling with probs (#3813)	Georgi Gerganov
2023-10-28	common : print that one line of the syntax help also to standard output (#3...	Henk Poley
2023-10-23	llama : remove token functions with `context` args in favor of `model` (#3720)	Marcus Dunn