ggerganov/llama.cpp

Pull Requests Commits

ggml-webgpu: Fix WASM compilation with OpenMP (#25943)

reeselevine committed 106 days ago

Verified 7cdd557f

common : use-after-free when loading LoRA adapter fails (#25611)

nmouha committed 107 days ago

Verified 8bb90937

server: support MCP stdio (#26062)

ngxson committed 107 days ago

Verified 20455a4a

hexagon: partial im2col support (#26007)

tboinovski1 committed 107 days ago

Verified 355303ed

common : skip empty implicit default preset (#25643)

hogeheer499-commits committed 107 days ago

Verified c812c543

server: add format arg to datetime tool (#26117)

ngxson committed 107 days ago

Verified abc34879

server : add missing task parameters(adaptive_target, adaptive_decay) in generation_settings (#25830)

tekinertekin committed 107 days ago

Verified 2cfc7670

vendor : update cpp-httplib to 0.51.0 (#26067)

angt committed 107 days ago

Verified 720d7fa4

Update ggml/src/gguf.cpp : Defined virtual keyword for destructor of gguf_writer_base (#25867)

yymin1022 committed 107 days ago

Verified fb92d8f1

common : add support for multiple end sequences in the reasoning budget sampler (#25544)

aldehir committed 107 days ago

Verified 910196f6

tests: synchronize save-load-state generation (#26056)

helanfxz committed 107 days ago

Verified d67c0b41

ui: reduce per-token render cost when streaming (#26053)

Zach Winter committed 108 days ago

Verified 555881eb

ui: remove render effects (#26083)

ServeurpersoCom committed 108 days ago

Verified 96013c51

model: add GLM 5.2 Indexer support (#25407)

pcuenca committed 108 days ago

Verified 88bfee14

ui: fix MCP server display name conflicts in tools lists (#26011)

ServeurpersoCom committed 108 days ago

Verified 95a923a6

server: support "reasoning_effort": "none" in OAI API (#26045)

pnb committed 108 days ago

Verified 27209a59

llama: various bug fixes (#26051)

ngxson committed 108 days ago

Verified 298219f9

HIP: remove rocWMMA FlashAttention (#26046)

JohannesGaessler committed 108 days ago

Verified fa72aecc

opencl: cache compiled cl_program binaries on disk (#26050)

wanghqc committed 108 days ago

Verified ed7adbfe

opencl: do not treat NULL-mask flash attention as causal (#25771)

kumaal committed 108 days ago

Verified 56a83860

skill: create `add-new-model` and `code-review` (#26042)

ngxson committed 108 days ago

Verified 77095ee0

UI: Fix settings precedence, Factory < Admin (--ui-config-file) < Users (Settings panel) (#26002)

ServeurpersoCom committed 108 days ago

Verified 54ce507b

cohere2 moe template parser: enforce JSON schema for text responses if a response schema is provided (#26018)

boondocklabs committed 108 days ago

Verified 8f5ab832

vendor: update subprocess.h (#26061)

ngxson committed 108 days ago

Verified 0cea3622

hexagon: further improved pipeline of the core bits (L2, DMA, MM, FA) (#26049)

max-krasnyansky committed 108 days ago

Verified 0a50d990

hexagon: fix Windows crash when op_poll is enabled (#26029)

adgup committed 109 days ago

Verified c0bc8591

CUDA: fix external compilation of q1_0 MMQ (#25778)

JohannesGaessler committed 109 days ago

Verified 1425386f

args: refactor mlock/mmap/directio into load-mode (#20834)

taronaeo committed 109 days ago

Verified e6dd0e29

contrib: fix leftovers from the AI usage policy update (#26030)

ServeurpersoCom committed 109 days ago

Verified da296d6e

metal : add f16 type support to leaky relu (#25981)

iliailmer committed 109 days ago

Verified c588c4f4

Newer Older