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

2024-07-23	Joe Todd	sycl : Add support for non-release DPC++ & oneMKL ...	commit \| commitdiff \| tree
2024-07-23	Georgi Gerganov	llama : move vocab, grammar and sampling into separate...	commit \| commitdiff \| tree
2024-07-23	0cc4m	Vulkan IQ4_NL Support (#8613)	commit \| commitdiff \| tree
2024-07-23	Jeroen Mostert	Allow all RDNA2 archs to use sdot4 intrinsic (#8629)	commit \| commitdiff \| tree
2024-07-23	Georgi Gerganov	contrib : clarify PR squashing + module names (#8630)	commit \| commitdiff \| tree
2024-07-23	luoyu-intel	[SYCL] fix scratch size of softmax (#8642)	commit \| commitdiff \| tree
2024-07-22	Keke Han	llama : fix codeshell support (#8599)	commit \| commitdiff \| tree
2024-07-22	Jason Stillerman	llama : add support for SmolLm pre-tokenizer (#8609)	commit \| commitdiff \| tree
2024-07-22	Jiří Podivín	*.py: Stylistic adjustments for python (#8233)	commit \| commitdiff \| tree
2024-07-22	Georgi Gerganov	llama : allow overrides for tokenizer flags (#8614)	commit \| commitdiff \| tree
2024-07-22	Georgi Gerganov	tests : re-enable tokenizer tests (#8611)	commit \| commitdiff \| tree
2024-07-22	Douglas Hanley	llama : add Mistral Nemo inference support (#8604)	commit \| commitdiff \| tree
2024-07-22	Jan Boon	server : update doc to clarify n_keep when there is...	commit \| commitdiff \| tree
2024-07-22	Mark Zhuang	ggml: fix compile error for RISC-V (#8623)	commit \| commitdiff \| tree
2024-07-22	devojony	examples: fix android example cannot be generated conti...	commit \| commitdiff \| tree
2024-07-21	Georgi Gerganov	flake.lock: Update (#8610)	commit \| commitdiff \| tree
2024-07-21	M-A	examples : Rewrite pydantic_models_to_grammar_examples...	commit \| commitdiff \| tree
2024-07-21	compilade	gguf-py : fix some metadata name extraction edge cases...	commit \| commitdiff \| tree
2024-07-21	compilade	convert_hf : fix Gemma v1 conversion (#8597)	commit \| commitdiff \| tree
2024-07-20	Johannes Gäßler	CUDA: MMQ code deduplication + iquant support (#8495)	commit \| commitdiff \| tree
2024-07-20	Georgi Gerganov	gguf : handle null name during init (#8587)	commit \| commitdiff \| tree
2024-07-20	Michael Coppola	llama : add support for Tekken pre-tokenizer (#8579)	commit \| commitdiff \| tree
2024-07-20	Huifeng Ou	llama.swiftui: fix end of generation bug (#8268)	commit \| commitdiff \| tree
2024-07-20	Brian	gguf_dump.py: fix markddown kv array print (#8588)	commit \| commitdiff \| tree
2024-07-19	slaren	ggml : fix quant dot product with odd number of blocks...	commit \| commitdiff \| tree
2024-07-19	Brian	convert-*.py: remove add_name from ChatGLMModel class...	commit \| commitdiff \| tree
2024-07-19	Georgi Gerganov	llama : bump max layers from 256 to 512 (#8530)	commit \| commitdiff \| tree
2024-07-19	Georgi Gerganov	readme : fix server badge	commit \| commitdiff \| tree
2024-07-19	Clint Herron	ggml : add friendlier error message to fopen errors...	commit \| commitdiff \| tree
2024-07-19	Frank Mai	fix: typo of chatglm4 chat tmpl (#8586)	commit \| commitdiff \| tree
2024-07-19	Brian	convert-*.py: add general.name kv override (#8571)	commit \| commitdiff \| tree
2024-07-18	Johannes Gäßler	CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)	commit \| commitdiff \| tree
2024-07-18	65a	cmake : install all ggml public headers (#8480)	commit \| commitdiff \| tree
2024-07-18	Eric Zhang	server: use relative routes for static files in new...	commit \| commitdiff \| tree
2024-07-18	Brian	convert-*.py: GGUF Naming Convention Refactor and Metad...	commit \| commitdiff \| tree
2024-07-18	RunningLeon	server : respect `--special` cli arg (#8553)	commit \| commitdiff \| tree
2024-07-17	Johannes Gäßler	lookup: fibonacci hashing, fix crashes (#8548)	commit \| commitdiff \| tree
2024-07-17	Al Mochkin	build : Fix docker build warnings (#8535) (#8537)	commit \| commitdiff \| tree
2024-07-17	Brian	CONTRIBUTING.md : remove mention of noci (#8541)	commit \| commitdiff \| tree
2024-07-17	hipudding	[CANN] Add Ascend NPU backend (#6035)	commit \| commitdiff \| tree
2024-07-17	Masaya, Kato	batched: fix n_predict parameter (#8527)	commit \| commitdiff \| tree
2024-07-17	Georgi Gerganov	llama : disable context-shift for DeepSeek v2 (#8501)	commit \| commitdiff \| tree
2024-07-16	Johannes Gäßler	make/cmake: add missing force MMQ/cuBLAS for HIP (...	commit \| commitdiff \| tree
2024-07-16	Brian	gguf-hash : update clib.json to point to original xxhas...	commit \| commitdiff \| tree
2024-07-16	Steve Bonds	export-lora : handle help argument (#8497)	commit \| commitdiff \| tree
2024-07-16	Georgi Gerganov	llama : valign + remove unused ftype (#8502)	commit \| commitdiff \| tree
2024-07-16	compilade	convert_hf : faster lazy safetensors (#8482)	commit \| commitdiff \| tree
2024-07-15	Xuan Son Nguyen	Refactor lora adapter support (#8332)	commit \| commitdiff \| tree
2024-07-15	Xuan Son Nguyen	fix ci (#8494)	commit \| commitdiff \| tree
2024-07-15	Daniel Bevenius	ggml : suppress unknown pragma 'GCC' on windows (#8460)	commit \| commitdiff \| tree
2024-07-15	M-A	server: update README.md with llama-server --help outpu...	commit \| commitdiff \| tree
2024-07-15	Georgi Gerganov	common : add --no-cont-batching arg (#6358)	commit \| commitdiff \| tree
2024-07-15	NikolaiLyssogor	docs: fix links in development docs [no ci] (#8481)	commit \| commitdiff \| tree
2024-07-15	Meng, Hengyu	[SYCL] add concat through dim 1/2 (#8483)	commit \| commitdiff \| tree
2024-07-15	Georgi Gerganov	llama : de-duplicate deepseek2 norm	commit \| commitdiff \| tree
2024-07-15	0cc4m	Vulkan MMQ Fix (#8479)	commit \| commitdiff \| tree
2024-07-14	compilade	pydantic : replace uses of __annotations__ with get_typ...	commit \| commitdiff \| tree
2024-07-14	Georgi Gerganov	flake.lock: Update (#8475)	commit \| commitdiff \| tree
2024-07-14	Georgi Gerganov	llama : fix Gemma-2 Query scaling factors (#8473)	commit \| commitdiff \| tree
2024-07-14	Brian	gguf_hash.py: Add sha256 (#8470)	commit \| commitdiff \| tree
2024-07-14	compilade	llama : fix pre-tokenization of non-special added token...	commit \| commitdiff \| tree
2024-07-13	bandoti	vulkan : cmake integration (#8119)	commit \| commitdiff \| tree
2024-07-13	Georgi Gerganov	metal : template-ify some of the kernels (#8447)	commit \| commitdiff \| tree
2024-07-12	Georgi Gerganov	server : handle content array in chat API (#8449)	commit \| commitdiff \| tree
2024-07-12	Georgi Gerganov	main : print error on empty input (#8456)	commit \| commitdiff \| tree
2024-07-12	Daniel Bevenius	llama : suppress unary minus operator warning (#8448)	commit \| commitdiff \| tree
2024-07-12	Douglas Hanley	server : ensure batches are either all embed or all...	commit \| commitdiff \| tree
2024-07-12	Armen Kaleshian	docker : fix filename for convert-hf-to-gguf.py in...	commit \| commitdiff \| tree
2024-07-12	Jiří Podivín	convert : remove fsep token from GPTRefactForCausalLM...	commit \| commitdiff \| tree
2024-07-12	Georgi Gerganov	examples : sprintf -> snprintf (#8434)	commit \| commitdiff \| tree
2024-07-12	Georgi Gerganov	ggml : minor naming changes (#8433)	commit \| commitdiff \| tree
2024-07-12	Chen Xi	[SYCL] fix the mul_mat_id ut issues (#8427)	commit \| commitdiff \| tree
2024-07-11	Nicholai Tukanov	ggml : add NVPL BLAS support (#8329) (#8425)	commit \| commitdiff \| tree
2024-07-11	Daniel Bevenius	cuda : suppress 'noreturn' warn in no_device_code ...	commit \| commitdiff \| tree
2024-07-11	Johannes Gäßler	CUDA: optimize and refactor MMQ (#8416)	commit \| commitdiff \| tree
2024-07-11	Georgi Gerganov	gitignore : deprecated binaries	commit \| commitdiff \| tree
2024-07-11	compilade	tokenize : add --no-parse-special option (#8423)	commit \| commitdiff \| tree
2024-07-11	Georgi Gerganov	llama : use F32 precision in Qwen2 attention and no...	commit \| commitdiff \| tree
2024-07-11	Clint Herron	Initialize default slot sampling parameters from the...	commit \| commitdiff \| tree
2024-07-10	Clint Herron	Name Migration: Build the deprecation-warning 'main...	commit \| commitdiff \| tree
2024-07-10	AidanBeltonS	[SYCL] Use multi_ptr to clean up deprecated warnings...	commit \| commitdiff \| tree
2024-07-10	Georgi Gerganov	ggml : move sgemm sources to llamafile subfolder (...	commit \| commitdiff \| tree
2024-07-10	Dibakar Gope	ggml : add AArch64 optimized GEMV and GEMM Q4 kernels...	commit \| commitdiff \| tree
2024-07-10	M. Yusuf Sarıgöz	gguf-py rel pipeline (#8410)	commit \| commitdiff \| tree
2024-07-10	Borislav Stanimirov	llama : C++20 compatibility for u8 strings (#8408)	commit \| commitdiff \| tree
2024-07-10	Borislav Stanimirov	msvc : silence codecvt c++17 deprecation warnings ...	commit \| commitdiff \| tree
2024-07-10	fairydreaming	llama : add assert about missing llama_encode() call...	commit \| commitdiff \| tree
2024-07-10	RunningLeon	py : fix converter for internlm2 (#8321)	commit \| commitdiff \| tree
2024-07-10	laik	py : fix extra space in convert_hf_to_gguf.py (#8407)	commit \| commitdiff \| tree
2024-07-09	Clint Herron	Server: Enable setting default sampling parameters...	commit \| commitdiff \| tree
2024-07-09	Andy Salerno	Update README.md to fix broken link to docs (#8399)	commit \| commitdiff \| tree
2024-07-09	Clint Herron	Deprecation warning to assist with migration to new...	commit \| commitdiff \| tree
2024-07-09	Johannes Gäßler	make/cmake: LLAMA_NO_CCACHE -> GGML_NO_CCACHE (#8392)	commit \| commitdiff \| tree
2024-07-09	Alberto Cabrera...	sycl : Reenabled mmvq path for the SYCL Nvidia Backend...	commit \| commitdiff \| tree
2024-07-09	Borislav Stanimirov	cmake : allow external ggml (#8370)	commit \| commitdiff \| tree
2024-07-09	daghanerdonmez	readme : fix typo [no ci] (#8389)	commit \| commitdiff \| tree
2024-07-09	compilade	gguf-py : do not use internal numpy types (#7472)	commit \| commitdiff \| tree
2024-07-08	Georgi Gerganov	flake.lock: Update (#8342)	commit \| commitdiff \| tree
2024-07-08	Alberto Cabrera...	labeler : updated sycl to match docs and code refactor...	commit \| commitdiff \| tree
2024-07-08	b4b4o	readme : fix web link error [no ci] (#8347)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom