2024-02-25 |
Ashok Gelal | readme : add Msty to UI list (#5618) |
commit | commitdiff | tree |
2024-02-25 |
Pierrick Hymbert | server: logs - unified format and --log-format option... |
commit | commitdiff | tree |
2024-02-25 |
Pierrick Hymbert | server: concurrency fix + monitoring - add /metrics... |
commit | commitdiff | tree |
2024-02-25 |
Radosław Gryta | cmake : fix compilation for Android armeabi-v7a (#5702) |
commit | commitdiff | tree |
2024-02-25 |
Georgi Gerganov | code : normalize enum names (#5697) |
commit | commitdiff | tree |
2024-02-25 |
Anas Ahouzi | py : fix StableLM conversion after config.json changes... |
commit | commitdiff | tree |
2024-02-24 |
Pierrick Hymbert | server: continue to update other slots on embedding... |
commit | commitdiff | tree |
2024-02-24 |
Kawrakow | IQ3_S: a much better alternative to Q3_K (#5676) |
commit | commitdiff | tree |
2024-02-24 |
Pierrick Hymbert | server: init functional tests (#5566) |
commit | commitdiff | tree |
2024-02-23 |
AlpinDale | server : add KV cache quantization options (#5684) |
commit | commitdiff | tree |
2024-02-23 |
Jared Van Bortel | convert : fix missing ftype for gemma (#5690) |
commit | commitdiff | tree |
2024-02-22 |
Jared Van Bortel | mpt : do not duplicate token_embd.weight on disk (... |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | gemma : use more bits for the token_embd.weight tensor... |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | py : add Gemma conversion from HF models (#5647) |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | ggml : always define ggml_fp16_t as uint16_t (#5666) |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | ggml : 32-bit arm compat (whisper/1891) |
commit | commitdiff | tree |
2024-02-22 |
Someone | nix: init singularity and docker images (#5056) |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | py : minor fixes (#5668) |
commit | commitdiff | tree |
2024-02-22 |
Xuan Son Nguyen | Add Gemma chat template (#5665) |
commit | commitdiff | tree |
2024-02-22 |
Someone | workflows: nix: hardcode cachix ids, build unconditiona... |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | minor : fix trailing whitespace (#5638) |
commit | commitdiff | tree |
2024-02-22 |
Georgi Gerganov | readme : update hot topics |
commit | commitdiff | tree |
2024-02-22 |
Xuan Son Nguyen | server : fallback to chatml, add AlphaMonarch chat... |
commit | commitdiff | tree |
2024-02-22 |
Alexey Parfenov | server : clarify some params in the docs (#5640) |
commit | commitdiff | tree |
2024-02-22 |
Dat Quoc Nguyen | mpt : add optional bias tensors (#5638) |
commit | commitdiff | tree |
2024-02-21 |
slaren | llama : fix loading models with shared tok_embd and... |
commit | commitdiff | tree |
2024-02-21 |
Xuan Son Nguyen | Add docs for llama_chat_apply_template (#5645) |
commit | commitdiff | tree |
2024-02-21 |
slaren | llama : fix session save/load with quantized KV (#5649) |
commit | commitdiff | tree |
2024-02-21 |
slaren | gemma : allow offloading the output tensor (#5646) |
commit | commitdiff | tree |
2024-02-21 |
Jared Van Bortel | examples : do not assume BOS when shifting context... |
commit | commitdiff | tree |
2024-02-21 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
2024-02-21 |
Pierrick Hymbert | server: health: fix race condition on slots data using... |
commit | commitdiff | tree |
2024-02-21 |
Ettore Di Giacinto | readme : add LocalAI to the availables UI (#5629) |
commit | commitdiff | tree |
2024-02-21 |
Georgi Gerganov | sync : ggml (#5633) |
commit | commitdiff | tree |
2024-02-21 |
Georgi Gerganov | readme : update hot topics |
commit | commitdiff | tree |
2024-02-21 |
Daniel Bevenius | llava : add --skip-unknown to 1.6 convert.py (#5632) |
commit | commitdiff | tree |
2024-02-21 |
postmasters | llama : add `gemma` model (#5631) |
commit | commitdiff | tree |
2024-02-21 |
Meng, Hengyu | [SYCL] conext add name (#5624) |
commit | commitdiff | tree |
2024-02-21 |
Kawrakow | IQ4_NL: 4-bit non-linear quants with blocks of 32 ... |
commit | commitdiff | tree |
2024-02-20 |
CJ Pais | server : support llava 1.6 (#5553) |
commit | commitdiff | tree |
2024-02-20 |
slaren | make : fix debug build with CUDA (#5616) |
commit | commitdiff | tree |
2024-02-20 |
Daniel Bevenius | llava : add explicit instructions for llava-1.6 (#5611) |
commit | commitdiff | tree |
2024-02-20 |
Xuan Son Nguyen | Server: use llama_chat_apply_template (#5593) |
commit | commitdiff | tree |
2024-02-20 |
Dane Madsen | readme : update UI list (#5605) |
commit | commitdiff | tree |
2024-02-20 |
Haoxiang Fei | metal : add build system support for embedded metal... |
commit | commitdiff | tree |
2024-02-20 |
Pierrick Hymbert | server : health endpoint configurable failure on no... |
commit | commitdiff | tree |
2024-02-20 |
AidanBeltonS | Update ggml_sycl_op_mul_mat_vec_q (#5502) |
commit | commitdiff | tree |
2024-02-19 |
Mathijs de... | nix: now that we can do so, allow MacOS to build Vulkan... |
commit | commitdiff | tree |
2024-02-19 |
0cc4m | Enable Vulkan MacOS CI |
commit | commitdiff | tree |
2024-02-19 |
0cc4m | Refactor validation and enumeration platform checks... |
commit | commitdiff | tree |
2024-02-19 |
0cc4m | Add check for VK_KHR_portability_enumeration for Molten... |
commit | commitdiff | tree |
2024-02-19 |
Mathijs de... | Add preprocessor checks for Apple devices. |
commit | commitdiff | tree |
2024-02-19 |
Mathijs de... | Resolve ErrorIncompatibleDriver with Vulkan on MacOS. |
commit | commitdiff | tree |
2024-02-19 |
Mathijs de... | Allow for Vulkan build with Accelerate. |
commit | commitdiff | tree |
2024-02-19 |
slaren | cuda : ignore peer access already enabled errors (... |
commit | commitdiff | tree |
2024-02-19 |
Jared Van Bortel | make : pass CPPFLAGS directly to nvcc, not via -Xcompil... |
commit | commitdiff | tree |
2024-02-19 |
nopperl | examples : support minItems/maxItems in JSON grammar... |
commit | commitdiff | tree |
2024-02-19 |
Georgi Gerganov | llava : remove extra cont (#5587) |
commit | commitdiff | tree |
2024-02-19 |
slaren | llava : replace ggml_cpy with ggml_cont |
commit | commitdiff | tree |
2024-02-19 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
2024-02-19 |
Georgi Gerganov | ggml-alloc : apply ggml/731 |
commit | commitdiff | tree |
2024-02-19 |
Didzis Gosko | metal : option to embed MSL source into compiled binary... |
commit | commitdiff | tree |
2024-02-19 |
Georgi Gerganov | ci : enable -Werror for CUDA builds (#5579) |
commit | commitdiff | tree |
2024-02-19 |
Georgi Gerganov | make : fix CUDA build (#5580) |
commit | commitdiff | tree |
2024-02-19 |
valiray | readme : fix typo in README-sycl.md (#5353) |
commit | commitdiff | tree |
2024-02-19 |
Abhilash Majumder | cmake : remove obsolete sycl compile flags (#5581) |
commit | commitdiff | tree |
2024-02-19 |
Georgi Gerganov | minor : fix trailing whitespace (#5538) |
commit | commitdiff | tree |
2024-02-19 |
Daniel Bevenius | llava : avoid changing the original BakLLaVA model... |
commit | commitdiff | tree |
2024-02-19 |
NawafAlansari | baby-llama : allocate graphs in ggml_context (#5573) |
commit | commitdiff | tree |
2024-02-19 |
Xuan Son Nguyen | llama : add llama_chat_apply_template() (#5538) |
commit | commitdiff | tree |
2024-02-19 |
slaren | cuda, metal : fix nans in soft_max (#5574) |
commit | commitdiff | tree |
2024-02-19 |
Mirko185 | readme : update (#5572) |
commit | commitdiff | tree |
2024-02-19 |
bmwl | ggml : android and old glibc NUMA incompatibility bugfi... |
commit | commitdiff | tree |
2024-02-18 |
Jared Van Bortel | build : pass all warning flags to nvcc via -Xcompiler... |
commit | commitdiff | tree |
2024-02-18 |
Georgi Gerganov | ggml : restore vec dot stride arg names (#5453) |
commit | commitdiff | tree |
2024-02-18 |
Georgi Gerganov | ci : fix wikitext url + compile warnings (#5569) |
commit | commitdiff | tree |
2024-02-18 |
Georgi Gerganov | metal : fix unused warnings (#0) |
commit | commitdiff | tree |
2024-02-18 |
Robey Holderith | common, server : surface min_keep as its own parameter... |
commit | commitdiff | tree |
2024-02-18 |
Pierrick Hymbert | server : slots monitoring endpoint (#5550) |
commit | commitdiff | tree |
2024-02-18 |
Georgi Gerganov | sampling : do not set min_keep to n_probs (#5564) |
commit | commitdiff | tree |
2024-02-18 |
Georgi Gerganov | cmake : fix GGML_USE_SYCL typo (#5555) |
commit | commitdiff | tree |
2024-02-18 |
Pierrick Hymbert | server : enhanced health endpoint (#5548) |
commit | commitdiff | tree |
2024-02-18 |
Pierrick Hymbert | server : --n-predict option document and cap to max... |
commit | commitdiff | tree |
2024-02-18 |
Daniel Hiltgen | server : graceful server shutdown (#5244) |
commit | commitdiff | tree |
2024-02-18 |
Georgi Gerganov | common : fix ub (#5530) |
commit | commitdiff | tree |
2024-02-18 |
Herman Semenov | ggml, common, examples, tests : fixed type arguments... |
commit | commitdiff | tree |
2024-02-18 |
Daniel Bevenius | llava : update surgery script to not remove tensors... |
commit | commitdiff | tree |
2024-02-18 |
Kawrakow | 1.5 bit quantization (#5453) |
commit | commitdiff | tree |
2024-02-18 |
github-actions... | flake.lock: Update |
commit | commitdiff | tree |
2024-02-17 |
Georgi Gerganov | ggml : add ALiBi support for ggml_soft_max_ext (#5488) |
commit | commitdiff | tree |
2024-02-17 |
Ananta Bastola | ci : add an option to fail on compile warning (#3952) |
commit | commitdiff | tree |
2024-02-17 |
clibdev | gitignore : update for CLion IDE (#5544) |
commit | commitdiff | tree |
2024-02-16 |
Georgi Gerganov | cmake : fix VULKAN and ROCm builds (#5525) |
commit | commitdiff | tree |
2024-02-16 |
Georgi Gerganov | scripts : add helpers script for bench comparing commit... |
commit | commitdiff | tree |
2024-02-16 |
Herman Semenov | llava : removed excess free(NULL) operation (#5531) |
commit | commitdiff | tree |
2024-02-16 |
Herman Semenov | llama : minor fixed return int value (#5529) |
commit | commitdiff | tree |
2024-02-16 |
Alexey Parfenov | server : add "samplers" param to control the samplers... |
commit | commitdiff | tree |
2024-02-16 |
Rőczey Barnabás | server : fix system prompt cli (#5516) |
commit | commitdiff | tree |
2024-02-16 |
bmwl | ggml : add numa options (#5377) |
commit | commitdiff | tree |
next |