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

Age	Commit message (Expand)	Author
2024-01-24	llama : pre-allocate input tensors in a separate buffer (#5100)	slaren
2024-01-23	minor : clean-up some warnings and style (#5094)	Georgi Gerganov
2024-01-22	llama : fix not enough space in buffer with Qwen (#5086)	slaren
2024-01-22	llama : support StableLM 2 1.6B (#5052)	compilade
2024-01-22	llama : add Q3_K_XS (#5060)	Kawrakow
2024-01-22	llama : add more qwen2 models (#5071)	Shijie
2024-01-20	llama : run all KQV ops on the CPU with no KV offload (#5049)	slaren
2024-01-19	llama : support upcoming Qwen2 (#5037)	Shijie
2024-01-19	llama : add CodeShell support (#5016)	chiranko
2024-01-19	llama : fix falcon arch for tied output embeddings (#4978)	John
2024-01-18	llama : fix mlock with no-mmap with Metal (#5025)	slaren
2024-01-17	ggml : add IQ2 to test-backend-ops + refactoring (#4990)	Georgi Gerganov
2024-01-17	backend : add eval callback (#4935)	Georgi Gerganov
2024-01-17	llama : use Q4_K for attn_v for Q2_K_S when n_gqa >= 4 (#4996)	Kawrakow
2024-01-16	ggml : importance matrix support for legacy quants (#4969)	Kawrakow
2024-01-15	llama : apply classifier-free guidance to logits directly (#4951)	David Friehs
2024-01-15	llama : check for 256 divisibility for IQ2_XS, IQ2_XXS (#4950)	Kawrakow
2024-01-14	llama : fix missing quotes (#4937)	David Pflug
2024-01-14	llama : check LLAMA_TRACE env for extra logging (#4929)	Georgi Gerganov
2024-01-14	llama : use LLAMA_LOG_ macros for logging	Georgi Gerganov
2024-01-14	Fix ffn_down quantization mix for MoE models (#4927)	Kawrakow
2024-01-14	llama : support WinXP build with MinGW 8.1.0 (#3419)	Karthik Kumar Viswanathan
2024-01-14	2-bit quantizations (#4897)	Kawrakow
2024-01-14	Make Q3_K_S be the same as olf Q3_K_L for Mixtral-8x7B (#4906)	Kawrakow
2024-01-13	metal : remove old API (#4919)	Georgi Gerganov
2024-01-13	llama : fix detokenization of non-special added-tokens (#4916)	Georgi Gerganov
2024-01-13	llama : minimize size used for state save/load (#4820)	David Friehs
2024-01-13	convert : update phi-2 to latest HF repo (#4903)	Georgi Gerganov
2024-01-12	llama : ggml-backend integration (#4766)	slaren
2024-01-12	llama : remove redundant assert for StableLM (#4901)	Georgi Gerganov
2024-01-12	llama : fix typo "imp_embd" -> "inp_embd"	Georgi Gerganov
2024-01-12	llama : fix llm_build_k_shift to use correct n_rot (#4889)	Georgi Gerganov
2024-01-11	llama : restore intended k-quants mixes for MoE models (#4872)	Kawrakow
2024-01-11	ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)	Kawrakow
2024-01-11	main : print total token count and tokens consumed so far (#4874)	pudepiedj
2024-01-10	llama : add additional suffixes for model params (#4834)	Brian
2024-01-10	llama : recognize 1B phi models (#4847)	Austin
2024-01-08	SOTA 2-bit quants (#4773)	Kawrakow
2024-01-08	examples : add passkey test (#3856)	Georgi Gerganov
2024-01-07	llama : remove unused vars (#4796)	Georgi Gerganov
2024-01-07	llama : remove redundant GQA check (#4796)	Georgi Gerganov
2024-01-07	llama : print tensor meta for debugging	Georgi Gerganov
2024-01-02	llama : llama_model_desc print number of experts	Georgi Gerganov
2024-01-02	llama : replace all API facing `int`'s with `int32_t` (#4577)	Marcus Dunn
2024-01-02	llama : differentiate the KV dims in the attention (#4657)	postmasters
2023-12-30	ggml : add ggml_cpu_has_avx_vnni() (#4589)	automaticcat
2023-12-28	gpt2 : Add gpt2 architecture integration (#4555)	manikbhandari
2023-12-27	llama : add AWQ for llama, llama2, mpt, and mistral models (#4593)	Nam D. Tran
2023-12-26	cuda : fix vmm pool with multi GPU (#4620)	slaren
2023-12-24	llama : add PLaMo model (#3557)	Shintarou Okada