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

Age	Commit message (Expand)	Author
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
2024-02-08	fix trailing whitespace (#5407)	Johannes Gäßler
2024-02-08	llama : fix MiniCPM (#5392)	runfuture
2024-02-08	sampling: fix top_k <= 0 (#5388)	Johannes Gäßler
2024-02-07	Basic Vulkan Multi-GPU implementation (#5321)	0cc4m
2024-02-07	llama : add MiniCPM support (#5346)	runfuture
2024-02-05	iq3_xxs: quards for the no-imatrix situation (#5334)	Kawrakow
2024-02-03	YaRN : store rope scaling type as int32_t in memory (#5285)	Jared Van Bortel
2024-02-02	llama : fix memory leak in llama_batch_free (#5252)	Ian Bull
2024-02-01	llama : support InternLM2 (#5184)	Guoteng
2024-01-31	llama : reorder build_orion() at correct place (#5118)	Georgi Gerganov
2024-01-31	llama : remove LLAMA_MAX_DEVICES and LLAMA_SUPPORTS_GPU_OFFLOAD (#5240)	Georgi Gerganov
2024-01-30	Fix typos of IQ2_XXS and IQ3_XXS in llama.cpp (#5231)	Yiming Cui
2024-01-30	kompute : llama-bench support and ggml_cpu_has_kompute() (#5226)	Jared Van Bortel
2024-01-30	SOTA 3-bit quants (#5196)	Kawrakow
2024-01-29	kompute : fix fallback to CPU (#5201)	Jared Van Bortel
2024-01-29	Nomic Vulkan backend (#4456)	Jared Van Bortel
2024-01-29	fix typo "RLIMIT_MLOCK" (#5175)	divinity76
2024-01-28	ggml : add Vulkan backend (#2059)	0cc4m
2024-01-28	ggml : add unified SYCL backend for Intel GPUs (#2690)	Abhilash Majumder
2024-01-28	Apply min_p to unsorted tokens (#5115)	Johannes Gäßler
2024-01-28	Tests for min_p, sampling queue (#5147)	Johannes Gäßler
2024-01-28	llama : add support for Orion-14B (#5118)	sharpHL
2024-01-26	Another bucket sort (#5109)	Kawrakow
2024-01-25	llama : dynamic temperature sampling (#4972)	l3utterfly
2024-01-25	Fix Q3_K_XS for MoE models (#5113)	Kawrakow
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