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

Age	Commit message (Expand)	Author
2024-05-22	cuda : fix rope + add tests (#7452)	Georgi Gerganov
2024-05-21	llama : add phi3 128K model support (#7225)	liuwei-git
2024-05-18	ggml : fix quants nans when all the group weights are very close to zero (#7313)	slaren
2024-05-15	ggml : add `ggml_upscale_ext` (ggml/814)	John Balis
2024-05-14	metal : support FA without mask + add asserts (#7278)	Georgi Gerganov
2024-05-12	CUDA: add FP32 FlashAttention vector kernel (#7188)	Johannes Gäßler
2024-05-11	ggml : full ALiBi support (#7192)	Georgi Gerganov
2024-05-09	CUDA: generalize FP16 fattn vec kernel (#7061)	Johannes Gäßler
2024-05-08	ggml : introduce bfloat16 support (#6412)	Justine Tunney
2024-04-30	ggml : add Flash Attention (#5021)	Georgi Gerganov
2024-04-18	ggml : group all experts in a single ggml_mul_mat_id (#6505)	slaren
2024-04-16	llama : add qwen2moe (#6074)	Shijie
2024-04-12	metal : unify mul_mv_id kernels (#6556)	slaren
2024-04-03	ggml : mul_mat_id use the same tensor for all the experts (#6387)	slaren
2024-03-26	IQ1_M: 1.75 bpw quantization (#6302)	Kawrakow
2024-03-22	metal : pad n_ctx by 32 (#6177)	Georgi Gerganov
2024-03-13	test-backend-ops : skip CPU backend by default (#6028)	slaren
2024-03-09	ggml : remove old quantization functions (#5942)	Georgi Gerganov
2024-03-04	add some new ops, fix some operators and add batch operations to certain oper...	leejet
2024-02-27	IQ4_XS: a 4.25 bpw quantization (#5747)	Kawrakow
2024-02-26	Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range...	Kawrakow
2024-02-25	code : normalize enum names (#5697)	Georgi Gerganov
2024-02-24	IQ3_S: a much better alternative to Q3_K (#5676)	Kawrakow
2024-02-21	IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)	Kawrakow
2024-02-18	1.5 bit quantization (#5453)	Kawrakow
2024-02-17	ggml : add ALiBi support for ggml_soft_max_ext (#5488)	Georgi Gerganov
2024-02-13	tests : disable moe test (#5473)	Georgi Gerganov
2024-01-31	llava : add MobileVLM support (#5132)	JidongZhang-THU
2024-01-30	`ggml_cuda_cpy` support for 4d tensors and float16->float32 upcasting (ggml/686)	John Balis
2024-01-30	SOTA 3-bit quants (#5196)	Kawrakow
2024-01-29	Nomic Vulkan backend (#4456)	Jared Van Bortel
2024-01-28	ggml : add unified SYCL backend for Intel GPUs (#2690)	Abhilash Majumder
2024-01-27	Remove unused data and add fixes (#5154)	Michael Klimenko
2024-01-17	ggml : add IQ2 to test-backend-ops + refactoring (#4990)	Georgi Gerganov
2024-01-14	2-bit quantizations (#4897)	Kawrakow
2024-01-12	llama : ggml-backend integration (#4766)	slaren
2024-01-09	CUDA: faster softmax via shared memory + fp16 math (#4742)	Johannes Gäßler
2024-01-04	Print backend name on test-backend-ops failure (#4751)	Johannes Gäßler
2024-01-03	ggml : extend ggml_get_rows, ggml_repeat, ggml_concat (ggml/639)	Guillaume Wenzek
2024-01-02	metal : enable shader debugging (cmake option) (#4705)	Georgi Gerganov
2023-12-29	ggml : fix some mul mat cases + add tests for src1 F16 (ggml/669)	bssrdf
2023-12-21	ggml : change ggml_scale to take a float instead of tensor (#4573)	Georgi Gerganov
2023-12-18	llama : add phi-2 + fix NeoX rope + ggml_mul_mat_set_prec (#4490)	Ebey Abraham
2023-12-14	ggml : use ggml_row_size where possible (#4472)	slaren
2023-12-13	sync : ggml (SD ops, tests, kernels) (#4444)	Georgi Gerganov
2023-12-13	llama : add Mixtral support (#4406)	slaren
2023-12-07	sync : ggml (new ops, tests, backend, etc.) (#4359)	Georgi Gerganov