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

2024-05-22	Justine Tunney	llama : add missing model type names (#7445)	commit \| commitdiff \| tree
2024-05-22	Georgi Gerganov	cuda : fix compile warning (#7454)	commit \| commitdiff \| tree
2024-05-22	Johannes Gäßler	CUDA: remove incorrect precision check (#7454)	commit \| commitdiff \| tree
2024-05-22	Georgi Gerganov	cuda : fix rope + add tests (#7452)	commit \| commitdiff \| tree
2024-05-21	liuwei-git	llama : add phi3 128K model support (#7225)	commit \| commitdiff \| tree
2024-05-21	Georgi Gerganov	metal : handle F16 inf values, fix FA partial offload...	commit \| commitdiff \| tree
2024-05-21	Olivier Chafik	`grammars`: fix resampling logic regression (#7424)	commit \| commitdiff \| tree
2024-05-21	Johannes Gäßler	CUDA: fix unused warning in mmq.cu (#7442)	commit \| commitdiff \| tree
2024-05-21	Georgi Gerganov	tests : test-tokenizer-0.sh print more info (#7402)	commit \| commitdiff \| tree
2024-05-21	Amir	examples: cache hf model when --model not provided...	commit \| commitdiff \| tree
2024-05-21	Johannes Gäßler	CUDA: deduplicate mmq code (#7397)	commit \| commitdiff \| tree
2024-05-21	jaime-m-p	Tokenizer SPM fixes for phi-3 and llama-spm (bugfix...	commit \| commitdiff \| tree
2024-05-20	jaime-m-p	Tokenizer SPM fixes for phi-3 and llama-spm (#7375)	commit \| commitdiff \| tree
2024-05-20	Georgi Gerganov	llama : remove Persimmon (#7408)	commit \| commitdiff \| tree
2024-05-20	Johannes Gäßler	perplexity: update README FP16 results [no ci] (#7413)	commit \| commitdiff \| tree
2024-05-20	Radoslav Gerganov	rpc : track allocated buffers (#7411)	commit \| commitdiff \| tree
2024-05-20	Georgi Gerganov	server : fix temperature + disable some tests (#7409)	commit \| commitdiff \| tree
2024-05-20	AidanBeltonS	[SYCL] Update SYCL upscale operation (#7321)	commit \| commitdiff \| tree
2024-05-20	Bingan	Update README.md (#7410)	commit \| commitdiff \| tree
2024-05-20	Herman Semenov	ggml-opencl, llama: using reserve() if count already...	commit \| commitdiff \| tree
2024-05-20	junchao-loongson	ggml : add loongarch lsx and lasx support (#6454)	commit \| commitdiff \| tree
2024-05-20	Georgi Gerganov	server : tuning tests (#7388)	commit \| commitdiff \| tree
2024-05-20	Georgi Gerganov	server : return error on too large embedding input...	commit \| commitdiff \| tree
2024-05-20	Georgi Gerganov	tests : fix --keep_split -> --keep-split (#7374)	commit \| commitdiff \| tree
2024-05-20	Srihari-mcw	Add provisions for windows support for BF16 code includ...	commit \| commitdiff \| tree
2024-05-19	slaren	llama : remove MPI backend (#7395)	commit \| commitdiff \| tree
2024-05-19	Fred Douglas	quantize : fix --keep-split check (#7374)	commit \| commitdiff \| tree
2024-05-19	0cc4m	Vulkan Embedding Fix (#7360)	commit \| commitdiff \| tree
2024-05-19	slaren	ggml : fix another case of quants nans (#7387)	commit \| commitdiff \| tree
2024-05-19	Johannes Gäßler	ggml: implement quantized KV cache for FA (#7372)	commit \| commitdiff \| tree
2024-05-19	Johannes Gäßler	server: add test for token probs (#7347)	commit \| commitdiff \| tree
2024-05-19	Johannes Gäßler	server: fix seed being reported back (#7382)	commit \| commitdiff \| tree
2024-05-19	Anas Ahouzi	Add StableLM2 pre-tokenizer (#7349)	commit \| commitdiff \| tree
2024-05-19	slaren	cuda : clear error after buffer allocation failure...	commit \| commitdiff \| tree
2024-05-19	Brian	labeler.yml: Use settings from ggerganov/llama.cpp...	commit \| commitdiff \| tree
2024-05-19	Georgi Gerganov	cmake : update android comments (#7341)	commit \| commitdiff \| tree
2024-05-18	fraxy-v	Capture CUDA logging output (#7298)	commit \| commitdiff \| tree
2024-05-18	Georgi Gerganov	ci : re-enable sanitizer runs (#7358)	commit \| commitdiff \| tree
2024-05-18	Georgi Gerganov	android : use "ci-android" branch for CI (#7341)	commit \| commitdiff \| tree
2024-05-18	Johannes Gäßler	CUDA: deduplicate FlashAttention code (#7352)	commit \| commitdiff \| tree
2024-05-18	Johannes Gäßler	server: correct --threads documentation [no ci] (#7362)	commit \| commitdiff \| tree
2024-05-18	Engininja2	cuda : add half2 __shfl_xor() for ROCm 5.5 (#7263)	commit \| commitdiff \| tree
2024-05-18	Steffen Röcker	llama : add support for larger Granite Code Models...	commit \| commitdiff \| tree
2024-05-18	strawberrymelonpanda	perplexity : ndot progress and show stats with < 100...	commit \| commitdiff \| tree
2024-05-18	0cc4m	Update and fix Vulkan soft_max and argsort implementati...	commit \| commitdiff \| tree
2024-05-18	Brian	github-actions-labeler: initial commit (#7330)	commit \| commitdiff \| tree
2024-05-18	Georgi Gerganov	convert : fix set_vocab_sentencepiece (#6866)	commit \| commitdiff \| tree
2024-05-18	slaren	ggml : fix quants nans when all the group weights are...	commit \| commitdiff \| tree
2024-05-18	Engininja2	cmake : fix typo in AMDGPU_TARGETS (#7356)	commit \| commitdiff \| tree
2024-05-17	jaime-m-p	Unicode codepoint flags for custom regexs (#7245)	commit \| commitdiff \| tree
2024-05-17	Johannes Gäßler	CUDA: faster large batch FA without tensor cores (...	commit \| commitdiff \| tree
2024-05-17	Gavin Zhao	ROCm: use native CMake HIP support (#5966)	commit \| commitdiff \| tree
2024-05-17	Radoslav Gerganov	rpc : set SO_REUSEADDR for the server socket (#7320)	commit \| commitdiff \| tree
2024-05-17	Brian	Added a single test function script and fix debug-test...	commit \| commitdiff \| tree
2024-05-17	Aarni Koskela	py : convert-hf-to-gguf-update improvements (#7340)	commit \| commitdiff \| tree
2024-05-17	fairydreaming	llama : use n_embd_head_v when reshaping kqv (#7327)	commit \| commitdiff \| tree
2024-05-17	Johannes Gäßler	tokenization: add warning for double BOS (#7332)	commit \| commitdiff \| tree
2024-05-17	Herman Semenov	ggml-quants, llama : removed excess checks (#7274)	commit \| commitdiff \| tree
2024-05-17	amd-lalithnc	convert : fix Qwen/Qwen-7b conversion (#7308)	commit \| commitdiff \| tree
2024-05-17	Radoslav Gerganov	server : add support for the RPC backend (#7305)	commit \| commitdiff \| tree
2024-05-17	Justine Tunney	ggml : rewrite silu and softmax for cpu (#7154)	commit \| commitdiff \| tree
2024-05-17	Leon Knauer	[Server] Added --verbose option to README [no ci] ...	commit \| commitdiff \| tree
2024-05-16	Pierrick Hymbert	Revert "server bench: fix bench not waiting for model...	commit \| commitdiff \| tree
2024-05-16	Radoslav Gerganov	rpc : get available mem for the CPU backend	commit \| commitdiff \| tree
2024-05-16	Radoslav Gerganov	rpc : add command line arg for specifying backend memory	commit \| commitdiff \| tree
2024-05-16	Jared Van Bortel	convert : get general.name from model dir, not its...	commit \| commitdiff \| tree
2024-05-16	Herman Semenov	grammar, json, llama: replace push on emplace if it...	commit \| commitdiff \| tree
2024-05-16	Vaibhav Srivastav	doc: add references to hugging face GGUF-my-repo quanti...	commit \| commitdiff \| tree
2024-05-16	Max Krasnyansky	ci: fix bin/Release path for windows-arm64 builds ...	commit \| commitdiff \| tree
2024-05-16	Max Krasnyansky	Add support for properly optimized Windows ARM64 builds...	commit \| commitdiff \| tree
2024-05-15	Daniel Bevenius	readme : remove stray double quote (#7310)	commit \| commitdiff \| tree
2024-05-15	kunnis	ggml : use dynamic thread scheduling for matrix multipl...	commit \| commitdiff \| tree
2024-05-15	agray3	Avoid unnecessarily disabling CUDA graphs (#7302)	commit \| commitdiff \| tree
2024-05-15	slaren	ggml : tag ggml_tensor::backend as deprecated (#7290)	commit \| commitdiff \| tree
2024-05-15	AidanBeltonS	Add missing " (#7303)	commit \| commitdiff \| tree
2024-05-15	dm4	embedding : free the batch after execution (#7297)	commit \| commitdiff \| tree
2024-05-15	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-05-15	John Balis	ggml : add `ggml_upscale_ext` (ggml/814)	commit \| commitdiff \| tree
2024-05-15	Johannes Gäßler	server bench: fix bench not waiting for model load...	commit \| commitdiff \| tree
2024-05-14	Georgi Gerganov	script : sync ggml-rpc	commit \| commitdiff \| tree
2024-05-14	Georgi Gerganov	metal : support FA without mask + add asserts (#7278)	commit \| commitdiff \| tree
2024-05-14	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-05-14	Georgi Gerganov	metal : tune soft_max number of threads (whisper/0)	commit \| commitdiff \| tree
2024-05-14	Georgi Gerganov	ggml : try fix ppc64 (whisper/0)	commit \| commitdiff \| tree
2024-05-14	Przemysław...	ggml : expose SSE3 and SSSE3 for MSVC when AVX is avail...	commit \| commitdiff \| tree
2024-05-14	Hong Bo PENG	ggml : optimize for ppc64le using VSX intrinsics (ggml...	commit \| commitdiff \| tree
2024-05-14	Steve Grubb	server: free sampling contexts on exit (#7264)	commit \| commitdiff \| tree
2024-05-14	Brian	Revert "move ndk code to a new library (#6951)" (#7282)	commit \| commitdiff \| tree
2024-05-14	Radoslav Gerganov	ggml : add RPC backend (#6829)	commit \| commitdiff \| tree
2024-05-14	slaren	llama : disable pipeline parallelism with nkvo (#7265)	commit \| commitdiff \| tree
2024-05-14	Elton Kola	move ndk code to a new library (#6951)	commit \| commitdiff \| tree
2024-05-14	Haggai Nuchi	Add left recursion check: quit early instead of going...	commit \| commitdiff \| tree
2024-05-14	Ryuei	docs: Fix typo and update description for --embeddings...	commit \| commitdiff \| tree
2024-05-13	compilade	convert-hf : support direct Q8_0 conversion (#7234)	commit \| commitdiff \| tree
2024-05-13	Georgi Gerganov	llama : less KV padding when FA is off (#7257)	commit \| commitdiff \| tree
2024-05-13	k.h.lai	llava-cli: fix base64 prompt (#7248)	commit \| commitdiff \| tree
2024-05-13	Johannes Gäßler	perplexity: add BF16 vs. FP16 results (#7150)	commit \| commitdiff \| tree
2024-05-13	Neo Zhang	[SYCL] rm wait() (#7233)	commit \| commitdiff \| tree
2024-05-13	Joan Fontanals	llama : rename jina tokenizers to v2 (#7249)	commit \| commitdiff \| tree
2024-05-13	Brian	convert.py: Outfile default name change and additional...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom