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

Age	Commit message (Expand)	Author
2024-03-02	llama : refactor internal quantization functions (#5830)	Xuan Son Nguyen
2024-03-02	llama : fix segfault from unknown model arch name (#5820)	compilade
2024-03-02	Support multiple GPUs (split mode) on SYCL backend (#5806)	Neo Zhang Jianyu
2024-03-01	llama : add StarCoder2 support (#5795)	Sourab Mangrulkar
2024-03-01	llama : cleanup unused mmq flags (#5772)	Pierrick Hymbert
2024-03-01	unicode : switch to multimap based nfd_map (#5799)	Douglas Hanley
2024-02-29	llama : constified `llama_set_state_data`'s `src` (#5774)	Marcus Dunn
2024-02-28	llama : remove deprecated API (#5770)	Georgi Gerganov
2024-02-28	llama : fix non-quantization of expert gating tensors (#5754)	compilade
2024-02-28	llama : improve BERT tokenization (#5740)	Douglas Hanley
2024-02-27	IQ4_XS: a 4.25 bpw quantization (#5747)	Kawrakow
2024-02-27	llama : fix defrag bugs + add parameter (#5735)	Georgi Gerganov
2024-02-26	Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range...	Kawrakow
2024-02-26	[SYCL] Add support for soft_max ALiBi (#5639)	AidanBeltonS
2024-02-26	llama : fix Gemma rope type (#5691)	Georgi Gerganov
2024-02-25	llama : refactor k-shift implementation + KV defragmentation (#5691)	Georgi Gerganov
2024-02-25	code : normalize enum names (#5697)	Georgi Gerganov
2024-02-24	IQ3_S: a much better alternative to Q3_K (#5676)	Kawrakow
2024-02-22	mpt : do not duplicate token_embd.weight on disk (#5670)	Jared Van Bortel
2024-02-22	gemma : use more bits for the token_embd.weight tensor (#5650)	Georgi Gerganov
2024-02-22	py : add Gemma conversion from HF models (#5647)	Georgi Gerganov
2024-02-22	Add Gemma chat template (#5665)	Xuan Son Nguyen
2024-02-22	minor : fix trailing whitespace (#5638)	Georgi Gerganov
2024-02-22	server : fallback to chatml, add AlphaMonarch chat template (#5628)	Xuan Son Nguyen
2024-02-22	mpt : add optional bias tensors (#5638)	Dat Quoc Nguyen
2024-02-22	llama : fix loading models with shared tok_embd and output (#5651)	slaren
2024-02-21	llama : fix session save/load with quantized KV (#5649)	slaren
2024-02-21	gemma : allow offloading the output tensor (#5646)	slaren
2024-02-21	llama : add `gemma` model (#5631)	postmasters
2024-02-21	IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)	Kawrakow
2024-02-20	Server: use llama_chat_apply_template (#5593)	Xuan Son Nguyen
2024-02-19	minor : fix trailing whitespace (#5538)	Georgi Gerganov
2024-02-19	llama : add llama_chat_apply_template() (#5538)	Xuan Son Nguyen
2024-02-18	1.5 bit quantization (#5453)	Kawrakow
2024-02-17	ggml : add ALiBi support for ggml_soft_max_ext (#5488)	Georgi Gerganov
2024-02-16	llama : minor fixed return int value (#5529)	Herman Semenov
2024-02-16	ggml : add numa options (#5377)	bmwl
2024-02-15	Use correct type of pooling for embedding models (#5500)	Douglas Hanley
2024-02-13	llama : add support for Nomic Embed (#5468)	Jared Van Bortel
2024-02-13	llama : allow raw byte in SPM vocabs; don't crash on nl 404 (#5478)	Aarni Koskela
2024-02-13	llama : make load error reporting more granular (#5477)	Aarni Koskela
2024-02-13	tests : multi-thread the tokenizer tests (#5474)	Georgi Gerganov
2024-02-13	llama : support batched embeddings (#5466)	Douglas Hanley
2024-02-13	bert : add tests + fix quantization (#5475)	Georgi Gerganov
2024-02-12	llama : fix quantization when tensors are missing (#5423)	Georgi Gerganov
2024-02-12	sync : ggml (#5452)	Georgi Gerganov
2024-02-11	Add support for BERT embedding models (#5423)	Douglas Hanley
2024-02-11	ggml : add mmla kernels for quantized GEMM (#4966)	snadampal
2024-02-09	llama : do not cap thread count when MoE on CPU (#5419)	Paul Tsochantaris
2024-02-08	llama : do not print "offloading layers" message in CPU-only builds (#5416)	slaren