git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog

overview / pkg / ggml / sources / llama.cpp / shortlog

2024-01-20	slaren	llama : run all KQV ops on the CPU with no KV offload...	commit \| commitdiff \| tree
2024-01-20	Herman Semenov	cmake : add support for ccache (#5002)	commit \| commitdiff \| tree
2024-01-20	adel boussaken	Add a dart/flutter binding to README.md (#4882)	commit \| commitdiff \| tree
2024-01-20	Kylin	cuda : fix compile error in jetson platform (#4975)	commit \| commitdiff \| tree
2024-01-19	Uzo Nweke	finetune : fix ggml_allocr lifetimes (tmp workaround...	commit \| commitdiff \| tree
2024-01-19	Georgi Gerganov	imatrix : add README.md	commit \| commitdiff \| tree
2024-01-19	Shijie	llama : support upcoming Qwen2 (#5037)	commit \| commitdiff \| tree
2024-01-19	Georgi Gerganov	py : fix flake8 lint	commit \| commitdiff \| tree
2024-01-19	Kawrakow	winogrande: evaluate log-probs in parallel (#5036)	commit \| commitdiff \| tree
2024-01-19	chiranko	llama : add CodeShell support (#5016)	commit \| commitdiff \| tree
2024-01-19	Kawrakow	perplexity: avoid unnecessary alloocations and logit...	commit \| commitdiff \| tree
2024-01-19	Georgi Gerganov	perplexity : faster Winogrande via batching (#5024)	commit \| commitdiff \| tree
2024-01-18	John	llama : fix falcon arch for tied output embeddings...	commit \| commitdiff \| tree
2024-01-18	Georgi Gerganov	cmake : add ggml public headers (#5011)	commit \| commitdiff \| tree
2024-01-18	Xuan Son Nguyen	server : defer tasks when "slot unavailable" (#5018)	commit \| commitdiff \| tree
2024-01-18	slaren	llama : fix mlock with no-mmap with Metal (#5025)	commit \| commitdiff \| tree
2024-01-18	Georgi Gerganov	imatrix : fix assert for src0 non-cont check	commit \| commitdiff \| tree
2024-01-18	Georgi Gerganov	perplexity : fix winogrande N tasks option	commit \| commitdiff \| tree
2024-01-18	Georgi Gerganov	scripts : add get-winogrande.sh	commit \| commitdiff \| tree
2024-01-18	David Sommers	convert.py : fix llama/llama2 conversion due to vocab_s...	commit \| commitdiff \| tree
2024-01-18	Kawrakow	HellaSwag: speed up by parallelizing log-prob evaluatio...	commit \| commitdiff \| tree
2024-01-18	Georgi Gerganov	perplexity : faster HellaSwag via batching (#5017)	commit \| commitdiff \| tree
2024-01-18	Kawrakow	Add Winogrande evaluation (#5015)	commit \| commitdiff \| tree
2024-01-18	Georgi Gerganov	scritps : add helper script to get hellaswag data in...	commit \| commitdiff \| tree
2024-01-18	Paul Tsochantaris	metal : fix memory leak, dangling pointer and unused...	commit \| commitdiff \| tree
2024-01-17	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-01-17	Georgi Gerganov	ggml : add IQ2 to test-backend-ops + refactoring (...	commit \| commitdiff \| tree
2024-01-17	Georgi Gerganov	imatrix : offload to GPU support (#4957)	commit \| commitdiff \| tree
2024-01-17	Georgi Gerganov	backend : add eval callback (#4935)	commit \| commitdiff \| tree
2024-01-17	Georgi Gerganov	metal : create autorelease pool during library build...	commit \| commitdiff \| tree
2024-01-17	Georgi Gerganov	py : fix whitespace	commit \| commitdiff \| tree
2024-01-17	Georgi Gerganov	py : fix missing added_tokens_dict for SPM and BPE...	commit \| commitdiff \| tree
2024-01-17	Kawrakow	llama : use Q4_K for attn_v for Q2_K_S when n_gqa ...	commit \| commitdiff \| tree
2024-01-17	Paul Tsochantaris	metal : remove unnecessary nil check (#4986)	commit \| commitdiff \| tree
2024-01-17	David Renshaw	llama : fix copy/paste error in llama_sampling_params...	commit \| commitdiff \| tree
2024-01-16	Georgi Gerganov	py : remove unnecessary hasattr (#4903)	commit \| commitdiff \| tree
2024-01-16	Philip Taron	nix: remove nixConfig from flake.nix (#4984)	commit \| commitdiff \| tree
2024-01-16	Daniel Bevenius	finetune : add training data file to log message (...	commit \| commitdiff \| tree
2024-01-16	Kawrakow	ggml : importance matrix support for legacy quants...	commit \| commitdiff \| tree
2024-01-16	Maximilian...	examples : add complete parallel function calling examp...	commit \| commitdiff \| tree
2024-01-16	Georgi Gerganov	perplexity : fix kv cache handling for hellaswag (...	commit \| commitdiff \| tree
2024-01-16	Georgi Gerganov	flake.lock: update flake-parts, flake-parts/nixpkgs...	commit \| commitdiff \| tree
2024-01-16	Paul Tsochantaris	metal : localized logic in `ggml_metal_graph_compute...	commit \| commitdiff \| tree
2024-01-16	Neuman Vong	android : introduce starter project example (#4926)	commit \| commitdiff \| tree
2024-01-16	Alex Azarov	metal : replace loop of dispatch_async with dispatch_ap...	commit \| commitdiff \| tree
2024-01-16	Alex Azarov	metal : log `recommendedMaxWorkingSetSize` on iOS 16...	commit \| commitdiff \| tree
2024-01-16	Maximilian...	examples : fix and improv docs for the grammar generato...	commit \| commitdiff \| tree
2024-01-16	Justine Tunney	ggml : introduce GGML_CALL function annotation (#4850)	commit \| commitdiff \| tree
2024-01-16	Daniel Bevenius	finetune : use LLAMA_FILE_MAGIC_GGLA (#4961)	commit \| commitdiff \| tree
2024-01-16	stduhpf	speculative : threading options (#4959)	commit \| commitdiff \| tree
2024-01-15	ngc92	pass cpu-architecture arguments only to host code ...	commit \| commitdiff \| tree
2024-01-15	David Friehs	llama : apply classifier-free guidance to logits direct...	commit \| commitdiff \| tree
2024-01-15	Victor Z. Peng	awq-py : fix typo in awq-py/README.md (#4947)	commit \| commitdiff \| tree
2024-01-15	Georgi Gerganov	cuda : fix dequantize kernel names (#4938)	commit \| commitdiff \| tree
2024-01-15	Kawrakow	llama : check for 256 divisibility for IQ2_XS, IQ2_XXS...	commit \| commitdiff \| tree
2024-01-15	Kawrakow	CUDA: faster dequantize kernels for Q4_0 and Q4_1 ...	commit \| commitdiff \| tree
2024-01-14	David Pflug	llama : fix missing quotes (#4937)	commit \| commitdiff \| tree
2024-01-14	Kawrakow	Add ability to use importance matrix for all k-quants...	commit \| commitdiff \| tree
2024-01-14	Georgi Gerganov	llama : check LLAMA_TRACE env for extra logging (#4929)	commit \| commitdiff \| tree
2024-01-14	Georgi Gerganov	scripts : sync-ggml-am.sh option to skip commits	commit \| commitdiff \| tree
2024-01-14	Georgi Gerganov	llama : use LLAMA_LOG_ macros for logging	commit \| commitdiff \| tree
2024-01-14	Kawrakow	Fix ffn_down quantization mix for MoE models (#4927)	commit \| commitdiff \| tree
2024-01-14	Alex Azarov	metal : correctly set SIMD support flags on iOS (#4923)	commit \| commitdiff \| tree
2024-01-14	Karthik Kumar...	llama : support WinXP build with MinGW 8.1.0 (#3419)	commit \| commitdiff \| tree
2024-01-14	Kawrakow	2-bit quantizations (#4897)	commit \| commitdiff \| tree
2024-01-14	Kawrakow	Make Q3_K_S be the same as olf Q3_K_L for Mixtral-8x7B...	commit \| commitdiff \| tree
2024-01-13	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-01-13	Johannes Gäßler	ggml: cache sin/cos for RoPE (#4908)	commit \| commitdiff \| tree
2024-01-13	Georgi Gerganov	metal : remove old API (#4919)	commit \| commitdiff \| tree
2024-01-13	Georgi Gerganov	server : fix prompt caching with system prompt (#4914)	commit \| commitdiff \| tree
2024-01-13	Georgi Gerganov	llama : fix detokenization of non-special added-tokens...	commit \| commitdiff \| tree
2024-01-13	Georgi Gerganov	metal : disable log for loaded kernels (#4794)	commit \| commitdiff \| tree
2024-01-13	David Friehs	llama : minimize size used for state save/load (#4820)	commit \| commitdiff \| tree
2024-01-13	Someone	workflows: unbreak nix-build-aarch64, and split it...	commit \| commitdiff \| tree
2024-01-13	Yann Follet	main : add parameter --no-display-prompt (#4541)	commit \| commitdiff \| tree
2024-01-13	texmex76	gguf : fix potential infinite for-loop (#4600)	commit \| commitdiff \| tree
2024-01-13	Georgi Gerganov	metal : refactor kernel loading code (#4794)	commit \| commitdiff \| tree
2024-01-13	Johannes Gäßler	compare-llama-bench: tweak output format (#4910)	commit \| commitdiff \| tree
2024-01-13	Ziad Ben Hadj...	server : fix deadlock that occurs in multi-prompt scena...	commit \| commitdiff \| tree
2024-01-13	makomk	server : fix crash with multimodal models without BOS...	commit \| commitdiff \| tree
2024-01-13	Georgi Gerganov	convert : update phi-2 to latest HF repo (#4903)	commit \| commitdiff \| tree
2024-01-12	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-01-12	Georgi Gerganov	ggml : fix 32-bit ARM compat for IQ2_XS (whisper/1758)	commit \| commitdiff \| tree
2024-01-12	slaren	backend_sched : fix assignments	commit \| commitdiff \| tree
2024-01-12	Maximilian...	examples : add pydantic models to GBNF grammar generato...	commit \| commitdiff \| tree
2024-01-12	Johannes Gäßler	CUDA: faster q8_0 -> f16 dequantization (#4895)	commit \| commitdiff \| tree
2024-01-12	slaren	llama : ggml-backend integration (#4766)	commit \| commitdiff \| tree
2024-01-12	Georgi Gerganov	llama : remove redundant assert for StableLM (#4901)	commit \| commitdiff \| tree
2024-01-12	Daniel Bevenius	export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894)	commit \| commitdiff \| tree
2024-01-12	Zay	llama.swiftui : update models layout (#4826)	commit \| commitdiff \| tree
2024-01-12	Georgi Gerganov	gitignore : imatrix	commit \| commitdiff \| tree
2024-01-12	Johannes Gäßler	CUDA: fix softmax compile for old CUDA versions (#4862)	commit \| commitdiff \| tree
2024-01-12	Georgi Gerganov	llama : fix typo "imp_embd" -> "inp_embd"	commit \| commitdiff \| tree
2024-01-12	howlger	common : streamline the formatting of help (#4890)	commit \| commitdiff \| tree
2024-01-12	Georgi Gerganov	py : fix lint (#4889)	commit \| commitdiff \| tree
2024-01-12	Georgi Gerganov	llama : fix llm_build_k_shift to use correct n_rot...	commit \| commitdiff \| tree
2024-01-12	Kawrakow	Importance Matrix calculation (#4861)	commit \| commitdiff \| tree
2024-01-11	Georgi Gerganov	server : fix infill when prompt is empty (#4833)	commit \| commitdiff \| tree
2024-01-11	Georgi Gerganov	main : better name for variable n_print (#4874)	commit \| commitdiff \| tree
2024-01-11	Georgi Gerganov	main : disable token count by default (#4874)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom