ochafik/llama.cpp

Pull Requests Commits

ochafik committed 1 year ago

563a2bd0

server : update auto gen files comments [no ci] (#11484)

danbev committed 1 year ago

Verified e51c47b4

vulkan: Catch pipeline creation failure and print an error message (#11436)

jeffbolznv committed 1 year ago

Verified 2711d021

Parse https://ollama.com/library/ syntax (#11480)

ericcurtin committed 1 year ago

Verified f0d4b29e

ggerganov committed 1 year ago

Verified 81585779

ggml : add option to not print stack on abort (ggml/1081)

WilliamTambellini committed 1 year ago

Verified 1a0e87d2

ggml-cpu : fix ggml_graph_compute_thread did not terminate on abort. (ggml/1065)

issixx committed 1 year ago

Verified d2e518e9

embedding : enable --no-warmup option (#11475)

danbev committed 1 year ago

Verified b636228c

llama: fix missing k_cache store for rwkv6qwen2 (#11445)

MollySophia committed 1 year ago

Verified 325afb37

cmake: add hints for locating ggml on Windows using Llama find-package (#11466)

Emreerdog committed 1 year ago

Verified 794fe23f

server : Fixed wrong function name in llamacpp server unit test (#11473)

peidaqi committed 1 year ago

Verified cf8cc856

ci : fix build CPU arm64 (#11472)

ngxson committed 1 year ago

Verified d0c08040

HIP: Supress transformation warning in softmax.cu

IMbackK committed 1 year ago

Verified be5ef796

HIP: Only call rocblas_initialize on rocblas versions with the multiple instantation bug (#11080)

sARY77 committed 1 year ago

Verified cae9fb43

Add github protocol pulling and http:// (#11465)

ericcurtin committed 1 year ago

Verified 7fee2889

docker: allow installing pip packages system-wide (#11437)

rare-magma committed 1 year ago

Verified d7d1ecca

cmake : don't fail on `GGML_CPU=OFF` (#11457)

someone13574 committed 1 year ago

Verified 4bf3119d

docker: add perplexity and bench commands to full image (#11438)

rare-magma committed 1 year ago

Verified f643120b

SYCL : SOFTMAX F16 mask support and other fixes (#11261)

qnixsynapse committed 1 year ago

Verified 6e84b0ab

Handle missing model in CLI parameters for llama-run (#11399)

engelmi committed 1 year ago

Verified 2b8525d5

Add new hf protocol for ollama (#11449)

ericcurtin committed 1 year ago

Verified a4417ddd

AMD: parse the architecture as supplied by gcnArchName (#11244)

Haus1 committed 1 year ago

Verified d6d24cd9

llama : minor fixes for up llama load model speed (#11448)

lexasub committed 1 year ago

Verified a5203b44

llama: refactor llama_decode_impl (#11381)

JohannesGaessler committed 1 year ago

Verified df984e01

metal: Handle null returned from MTLCreateSystemDefaultDevice() (#11441)

Ihar Hrachyshka committed 1 year ago

Verified acd38efe

docker : fix ARM build and Vulkan build (#11434)

ngxson committed 1 year ago

Verified caf773f2

metal : use residency sets (#11427)

ggerganov committed 1 year ago

Verified 178a7eb9

docker: add missing vulkan library to base layer and update to 24.04 (#11422)

rare-magma committed 1 year ago

Verified 6f53d8a6

cmake: add ggml find package (#11369)

mtmcp committed 1 year ago

Verified 19f65187

rpc: fix register position (#11424)

thxCode committed 1 year ago

Verified 1d8ee060

Older