]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-04-12 Georgi Gerganovimatrix : remove invalid assert (#6632)
2024-04-12 MasterYi1024Correct free memory and total memory. (#6630)
2024-04-12 Pierrick Hymberteval-callback: use ggml_op_desc to pretty print unary...
2024-04-12 Georgi Gerganovci : disable Metal for macOS-latest-cmake-x64 (#6628)
2024-04-12 Clint HerronOptimization: eliminate addition of redundant stacks...
2024-04-11 Clint HerronAs suggested by @slaren, disabling Metal for test to...
2024-04-11 NikolasRefactor Error Handling for CUDA (#6575)
2024-04-11 Olivier Chafikgrammars: 1.5x faster inference w/ complex grammars...
2024-04-11 Hugo Rousselci: download artifacts to release directory (#6612)
2024-04-11 Daniel Beveniusscripts : add --outdir option to hf.sh (#6600)
2024-04-11 Pierrick Hymberteval-callback: Example how to use eval callback for...
2024-04-10 Daniel Beveniusgguf : add option to not check tensor data (#6582)
2024-04-10 Ralph Soikaminor layout improvements (#6572)
2024-04-10 slarenllama : add model types for mixtral (#6589)
2024-04-10 slarenconvert.py : add consolidated.safetensors for mixtral...
2024-04-10 Pierrick Hymbertdocs : how to add a model (#6565)
2024-04-10 Artem Zinnatullinreadme : fix ROCm link (#6579)
2024-04-10 sjxxreadme : update UI list (#6560)
2024-04-09 Jiří Sejkorareadme: fix typo in amdgpu target name (#6573)
2024-04-09 Jared Van BortelBERT tokenizer fixes (#6498)
2024-04-09 Georgi Gerganovsync : ggml
2024-04-09 Ed Leeserver : detect search query to start webchat (#6554)
2024-04-09 Carolinabananallama : add Command R Plus support (#6491)
2024-04-09 Georgi Gerganovlicense : update copyright notice + add AUTHORS (#6405)
2024-04-08 Georgi Gerganovllama : fix attention layer count sanity check (#6550)
2024-04-08 kunnisComment explaining a decision (#6531)
2024-04-08 Georgi Gerganovquantize : fix precedence of cli args (#6541)
2024-04-08 Rick Gllama : support negative ith in llama_get_ API (#6519)
2024-04-08 Jan Boonllama : save and restore kv cache for single seq id...
2024-04-08 Abhilash Majumderremove row=1 cond (#6532)
2024-04-08 FiratAdding KodiBot to UI list (#6535)
2024-04-07 Mark FairbairnChange Windows AMD example to release build to make...
2024-04-07 Georgi Gerganovflake.lock: Update (#6517)
2024-04-07 DAN™Add GritLM as supported models. (#6513)
2024-04-07 Georgi Gerganovsync : ggml
2024-04-07 Slava Primenkoggml: bypass code incompatible with CUDA < 11.1 (whispe...
2024-04-07 Georgi Gerganovscripts : sync ggml-cuda folder
2024-04-07 limitedAtonementRun make to build the project (#6457)
2024-04-07 Neo Zhang Jianyusupport/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS...
2024-04-06 Georgi Gerganovsync : ggml
2024-04-06 Daniel Beveniusbackend : fix typo in scheduler documentation (ggml...
2024-04-06 Clint HerronTests: Added integration tests for GBNF parser (#6472)
2024-04-06 Pierrick Hymbertci: bench: support sse and fix prompt processing time...
2024-04-05 Briangguf.py : add licence and version to gguf writer (...
2024-04-05 Hoang Nguyenreadme : update UI list (#6503)
2024-04-05 Ting Sunbench : make n_batch and n_ubatch configurable in Batch...
2024-04-05 Ouadie EL FAROUKI[SYCL] Fixed minor bug when enabling FP16 for non intel...
2024-04-04 alexpinelreadme : add Dot to UI list (#6487)
2024-04-04 Jun Jiereadme : fix typo (#6481)
2024-04-04 Ed Lepedusserver: add cURL support to server Dockerfiles (#6474)
2024-04-04 Minsoo Cheongci: exempt master branch workflows from getting cancell...
2024-04-04 Ewout ter Hoevenbuild CI: Name artifacts (#6482)
2024-04-04 Shakhar Dasguptaserver: allow penalizing repetition of newlines on...
2024-04-04 Pierrick Hymbertci: bench fix concurrency for workflow trigger dispatch...
2024-04-04 limitedAtonementCorrect README link (#6458)
2024-04-04 Pierrick Hymbertci: bench: add more ftype, fix triggers and bot comment...
2024-04-04 Daniel Beveniuscommon: remove duplicate check for curl (#6471)
2024-04-04 Clint Herronexamples : add GBNF validator program (#5948)
2024-04-04 Georgi Gerganovserver : remove obsolete --memory-f32 option
2024-04-04 Xiao-Yong Jinserver : add option to disable KV offload (#6468)
2024-04-04 Clint Herronconvert : fix for lint error complaining of bare except...
2024-04-03 FattireA few small fixes to server's README docs (#6428)
2024-04-03 JH23Xserver : handle exception on wrong type in request...
2024-04-03 bryanSwkllama : add SEA-LION support (#6448)
2024-04-03 Ewout ter Hoevenci : update checkout, setup-python and upload-artifact...
2024-04-03 Ed Lepedusserver: add cURL support to `server.Dockerfile` (#6461)
2024-04-03 Francisco Meloreadme : add feature-rich rust bindings (#6465)
2024-04-03 Joycesecurity : create policy (#6354)
2024-04-03 Abhishek Gopinath KMissing tokenizer.model error during gguf conversion...
2024-04-03 kaizauAdd OpenChat, Alpaca, Vicuna chat templates (#6397)
2024-04-03 Georgi Gerganovreadme : update hot topics
2024-04-03 slarenggml : mul_mat_id use the same tensor for all the exper...
2024-04-03 Meng, Hengyu[SYCL] Disable iqx on windows as WA (#6435)
2024-04-01 Georgi Gerganovflake.lock: Update (#6402)
2024-04-01 Johannes Gäßlercompare-llama-bench.py: fix long hexsha args (#6424)
2024-04-01 Pierrick Hymbertci: server: verify deps are coherent with the commit...
2024-03-31 Georgi Gerganovreadme : update hot topics
2024-03-30 Pierrick Hymbertci: bench: fix Resource not accessible by integration...
2024-03-29 Mohammadreza... Fedora build update (#6388)
2024-03-29 Xuan Son Nguyensplit: allow --split-max-size option (#6343)
2024-03-29 0cc4mVulkan k-quant mmq and ggml-backend offload functionali...
2024-03-29 Georgi Gerganovsync : ggml (#6351)
2024-03-29 hxer7963[Model] Add support for xverse (#6301)
2024-03-29 Georgi Gerganovci : fix BGE wget (#6383)
2024-03-29 zhouwgreadme : add project (#6356)
2024-03-29 Matt Claytoncmake : add explicit metal version options (#6370)
2024-03-29 Daniel Beveniusllama : remove redundant reshape in build_kv_store...
2024-03-29 Pedro Cuencaconvert : allow conversion of Mistral HF models (#6144)
2024-03-28 Georgi Gerganovreadme : add notice for UI list
2024-03-28 Ouadie EL FAROUKI[SYCL] Revisited & updated SYCL build documentation...
2024-03-28 Jared Van Bortelconvert : refactor vocab selection logic (#6355)
2024-03-28 Ziang Wullava : fix MobileVLM (#6364)
2024-03-28 compiladellama : fix command-r inference when omitting outputs...
2024-03-28 Pierrick Hymbertci: bench: fix master not schedule, fix commit status...
2024-03-28 Ting Sundoc: fix outdated default value of batch size (#6336)
2024-03-28 Eric Zhangserver : stop gracefully on SIGTERM (#6348)
2024-03-28 hutlinix: removed unnessesary indentation
2024-03-28 hutlinix: moved blas availability check to package inputs...
2024-03-28 hutliusing blas.meta.available to check host platform
2024-03-28 hutlionly using explicit blas if hostPlatform is allowed
next