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

2025-01-08	Georgi Gerganov	llama : avoid hardcoded QK_K (#11061)	commit \| commitdiff \| tree
2025-01-08	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-01-08	Radoslav Gerganov	ggml : allow loading backend with env variable (ggml...	commit \| commitdiff \| tree
2025-01-08	Xuan Son Nguyen	ci : pin dependency to specific version (#11137)	commit \| commitdiff \| tree
2025-01-08	Georgi Gerganov	arg : option to exclude arguments from specific example...	commit \| commitdiff \| tree
2025-01-08	amritahs-ibm	llamafile : ppc64le MMA INT8 implementation (#10912)	commit \| commitdiff \| tree
2025-01-08	Georgi Gerganov	ci : fix cmake option (#11125)	commit \| commitdiff \| tree
2025-01-08	Mathieu Baudier	Disable GL_KHR_cooperative_matrix Vulkan extension...	commit \| commitdiff \| tree
2025-01-08	ag2s20150909	fix: Vulkan shader gen binary path when Cross-compiling...	commit \| commitdiff \| tree
2025-01-07	Johannes Gäßler	GGUF: C++ refactor, backend support, misc fixes (#11030)	commit \| commitdiff \| tree
2025-01-07	Diego Devesa	ggml-backend : only offload from host buffers (fix...	commit \| commitdiff \| tree
2025-01-07	Diego Devesa	ggml-backend : only offload from host buffers (#11120)	commit \| commitdiff \| tree
2025-01-07	Radoslav Gerganov	rpc : code cleanup (#11107)	commit \| commitdiff \| tree
2025-01-07	Akarshan Biswas	SYCL: Use get_multi_ptr instead of deprecated get_point...	commit \| commitdiff \| tree
2025-01-06	Eric Curtin	llama-run : fix context size (#11094)	commit \| commitdiff \| tree
2025-01-06	Georgi Gerganov	llama : remove unused headers (#11109)	commit \| commitdiff \| tree
2025-01-06	Xuan Son Nguyen	github : add cmd line field to bug report (#11090)	commit \| commitdiff \| tree
2025-01-06	Georgi Gerganov	server : fix extra BOS in infill endpoint (#11106)	commit \| commitdiff \| tree
2025-01-06	Xuan Son Nguyen	llama : remove check flash_attn with lora (#11104)	commit \| commitdiff \| tree
2025-01-06	Asghar Ghorbani	llama : prevent system info string accumulation across...	commit \| commitdiff \| tree
2025-01-06	Daniel Bevenius	llama : rename missed batch params/vars to ubatch ...	commit \| commitdiff \| tree
2025-01-06	Georgi Gerganov	llama : update llama_model API names (#11063)	commit \| commitdiff \| tree
2025-01-06	Georgi Gerganov	tokenize : escape the prompt (#11058)	commit \| commitdiff \| tree
2025-01-06	Georgi Gerganov	mmap : fix fileno macro clash (#11076)	commit \| commitdiff \| tree
2025-01-06	Georgi Gerganov	llama : use LLAMA_TOKEN_NULL (#11062)	commit \| commitdiff \| tree
2025-01-06	Georgi Gerganov	llama : use _impl suffix instead of _internal (#11060)	commit \| commitdiff \| tree
2025-01-06	Johannes Gäßler	CUDA: add BF16 support (#11093)	commit \| commitdiff \| tree
2025-01-04	0cc4m	Vulkan: Add device-specific blacklist for coopmat for...	commit \| commitdiff \| tree
2025-01-04	fairydreaming	llama : Add support for DeepSeek V3 (#11049)	commit \| commitdiff \| tree
2025-01-04	matt23654	[GGML][RPC] Support for models with non-512-aligned...	commit \| commitdiff \| tree
2025-01-04	DAN™	llama : add support for the cohere2 model architecture...	commit \| commitdiff \| tree
2025-01-04	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-01-04	Georgi Gerganov	ggml : do not install metal source when embed library...	commit \| commitdiff \| tree
2025-01-04	Daniel Bevenius	ggml : improve inputs log sched_print_assignments ...	commit \| commitdiff \| tree
2025-01-04	Gilad S.	fix: Vulkan shader gen binary path (#11037)	commit \| commitdiff \| tree
2025-01-03	Molly Sophia	common : disable KV cache shifting automatically for...	commit \| commitdiff \| tree
2025-01-03	Georgi Gerganov	metal : avoid uint (#11019)	commit \| commitdiff \| tree
2025-01-03	Georgi Gerganov	llama : refactor `src/llama.cpp` (#10902)	commit \| commitdiff \| tree
2025-01-02	Pierrick Hymbert	server: bench: minor fixes (#10765)	commit \| commitdiff \| tree
2025-01-02	Xuan Son Nguyen	server : allow using LoRA adapters per-request (#10994)	commit \| commitdiff \| tree
2025-01-02	Benson Wong	readme : add llama-swap to infrastructure section ...	commit \| commitdiff \| tree
2024-12-31	Srihari-mcw	ggml : fixes for AVXVNNI instruction set with MSVC...	commit \| commitdiff \| tree
2024-12-31	Xuan Son Nguyen	server : clean up built-in template detection (#11026)	commit \| commitdiff \| tree
2024-12-31	Xuan Son Nguyen	server : add OAI compat for /v1/completions (#10974)	commit \| commitdiff \| tree
2024-12-31	ymcki	convert : fix Llama-3_1-Nemotron-51B rope settings...	commit \| commitdiff \| tree
2024-12-31	Peter	common, examples, ggml : fix MSYS2 GCC compiler errors...	commit \| commitdiff \| tree
2024-12-30	Jeff Bolz	vulkan: optimize mul_mat for small values of N (#10991)	commit \| commitdiff \| tree
2024-12-30	ag2s20150909	android : fix llama_batch free (#11014)	commit \| commitdiff \| tree
2024-12-29	Jeff Bolz	vulkan: im2col and matmul optimizations for stable...	commit \| commitdiff \| tree
2024-12-29	Jeff Bolz	vulkan: Use push constant offset to handle misaligned...	commit \| commitdiff \| tree
2024-12-28	Isaac McFadyen	server: added more docs for response_fields field ...	commit \| commitdiff \| tree
2024-12-28	Alexey Parfenov	server : fix token duplication when streaming with...	commit \| commitdiff \| tree
2024-12-26	Eve	vulkan: multi-row k quants (#10846)	commit \| commitdiff \| tree
2024-12-26	Peter	examples, ggml : fix GCC compiler warnings (#10983)	commit \| commitdiff \| tree
2024-12-24	Reza Kakhki	server : add support for "encoding_format": "base64...	commit \| commitdiff \| tree
2024-12-24	Djip007	ggml : more perfo with llamafile tinyblas on x86_64...	commit \| commitdiff \| tree
2024-12-24	NeverLucky	server: allow filtering llama server response fields...	commit \| commitdiff \| tree
2024-12-24	Georgi Gerganov	llama : the WPM vocabs use the CLS token as BOS (#10930)	commit \| commitdiff \| tree
2024-12-24	Diego Devesa	ggml : use wstring for backend search paths (#10960)	commit \| commitdiff \| tree
2024-12-24	Diego Devesa	ggml : fix arm enabled features check (#10961)	commit \| commitdiff \| tree
2024-12-23	Diego Devesa	ggml : fix const usage in SSE path (#10962)	commit \| commitdiff \| tree
2024-12-23	Xuan Son Nguyen	server : fix missing model id in /model endpoint (...	commit \| commitdiff \| tree
2024-12-23	Xuan Son Nguyen	server : add system_fingerprint to chat/completion...	commit \| commitdiff \| tree
2024-12-23	Radoslav Gerganov	rpc-server : add support for the SYCL backend (#10934)	commit \| commitdiff \| tree
2024-12-23	Yun Dou	llama : support InfiniAI Megrez 3b (#10893)	commit \| commitdiff \| tree
2024-12-23	ymcki	llama : support for Llama-3_1-Nemotron-51B (#10669)	commit \| commitdiff \| tree
2024-12-23	Eric Curtin	llama-run : include temperature option (#10899)	commit \| commitdiff \| tree
2024-12-23	yuri@FreeBSD	ggml : fix run-time on FreeBSD in get_executable_path...	commit \| commitdiff \| tree
2024-12-22	Rudi Servo	devops : add docker-multi-stage builds (#10832)	commit \| commitdiff \| tree
2024-12-22	Billel Mokeddem	llama : add Falcon3 support (#10883)	commit \| commitdiff \| tree
2024-12-22	Jeff Bolz	vulkan: build fixes for 32b (#10927)	commit \| commitdiff \| tree
2024-12-21	Georgi Gerganov	convert : add BertForMaskedLM (#10919)	commit \| commitdiff \| tree
2024-12-21	Jeff Bolz	vulkan: optimize coopmat2 dequant functions (#10855)	commit \| commitdiff \| tree
2024-12-20	Adrien Gallouët	ggml-cpu: replace NEON asm with intrinsics in ggml_gemv...	commit \| commitdiff \| tree
2024-12-20	Akarshan Biswas	SYCL: Migrate away from deprecated ggml_tensor->backend...	commit \| commitdiff \| tree
2024-12-20	Xuan Son Nguyen	server : (UI) fix copy to clipboard function (#10916)	commit \| commitdiff \| tree
2024-12-20	Diego Devesa	ggml : add test for SVE and disable when it fails ...	commit \| commitdiff \| tree
2024-12-20	Molly Sophia	convert : fix RWKV v6 model conversion (#10913)	commit \| commitdiff \| tree
2024-12-19	Georgi Gerganov	clip : disable GPU support (#10896)	commit \| commitdiff \| tree
2024-12-19	Georgi Gerganov	llama : minor grammar refactor (#10897)	commit \| commitdiff \| tree
2024-12-19	Georgi Gerganov	tts : small QoL for easy model fetch (#10903)	commit \| commitdiff \| tree
2024-12-19	Xuan Son Nguyen	server : fix logprobs, make it OAI-compatible (#10783)	commit \| commitdiff \| tree
2024-12-19	Adrien Gallouët	ggml: fix arm build with gcc (#10895)	commit \| commitdiff \| tree
2024-12-19	Sukriti Sharma	llama : fix Roberta embeddings (#10856)	commit \| commitdiff \| tree
2024-12-19	fairydreaming	convert : Add support for Microsoft Phi-4 model (...	commit \| commitdiff \| tree
2024-12-19	Johannes Gäßler	tests: disable GGUF test for bad value size (#10886)	commit \| commitdiff \| tree
2024-12-19	Eric Curtin	llama-run : improve progress bar (#10821)	commit \| commitdiff \| tree
2024-12-18	Diego Devesa	ggml : fix arm build (#10890)	commit \| commitdiff \| tree
2024-12-18	Georgi Gerganov	tts : add OuteTTS support (#10784)	commit \| commitdiff \| tree
2024-12-18	Gaetan Bisson	server: avoid overwriting Authorization header (#10878)	commit \| commitdiff \| tree
2024-12-18	Georgi Gerganov	server : output embeddings for all tokens when pooling...	commit \| commitdiff \| tree
2024-12-18	Georgi Gerganov	server : add "tokens" output (#10853)	commit \| commitdiff \| tree
2024-12-18	Xuan Son Nguyen	server : (embeddings) using same format for "input...	commit \| commitdiff \| tree
2024-12-18	redbeard	docs: Fix HIP (née hipBLAS) in README (#10880)	commit \| commitdiff \| tree
2024-12-18	Diego Devesa	Revert "llama : add Falcon3 support (#10864)" (#10876)	commit \| commitdiff \| tree
2024-12-17	DAN™	Use model->gguf_kv for loading the template instead...	commit \| commitdiff \| tree
2024-12-17	Johannes Gäßler	tests: add tests for GGUF (#10830)	commit \| commitdiff \| tree
2024-12-17	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-12-17	Georgi Gerganov	cmake : fix "amd64" processor string (whisper/2638)	commit \| commitdiff \| tree
2024-12-17	gn64	vulkan : fix soft_max.comp division by zero (whisper...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom