ochafik/llama.cpp

Pull Requests Commits

ggml : fix apple OS check in ggml_print_backtrace (ggml/1229)

slaren committed 323 days ago

8b5e19ae

ggml : Fix missing backtrace on Linux (ggml/1228)

danielzgtg committed 323 days ago

60aea028

fix: check model pointer validity before use (#13631)

D2hugging committed 323 days ago

Verified 9c55e5c5

CANN: Support MOE Model MUL_MAT_ID (#13042)

noemotiovon committed 323 days ago

Verified 33d7aed4

server : added --no-prefill-assistant flag (#13608)

isaac-mcfadyen committed 324 days ago

Verified 6a2bc8bf

cmake: use the current build config for vulkan-shaders-gen (#13595)

giladgd committed 324 days ago

Verified e3a7cf6c

parallel : add option for non-shared and larger prompts (#13598)

ggerganov committed 325 days ago

Verified 518329b2

vulkan: move common FA code to flash_attn_base.comp (#13556)

jeffbolznv committed 325 days ago

Verified 2f5a4e1e

vulkan: use scalar FA rather than coopmat2 when N==1 (#13554)

jeffbolznv committed 325 days ago

Verified 4f41ee11

Support new common_chat_templates_inputs.enable_thinking across models

ochafik committed 325 days ago

506e712b

chat-parser: remove input from exception (llm output may contain PII)

ochafik committed 325 days ago

224101b4

llguidance : official v0.7.20 release (no actual changes) [noci] (#13594)

CoffeeVampir3 committed 325 days ago

Verified 3e0be1ca

server : do not return error out of context (with ctx shift disabled) (#13577)

ngxson committed 325 days ago

Verified 6aa892ec

webui : improve accessibility for visually impaired people (#13551)

ngxson committed 325 days ago

Verified aea9f8b4

readme : add list of dependencies and their license (#13591)

ngxson committed 325 days ago

Verified 06c1e4ab

releases : use arm version of curl for arm releases (#13592)

slaren committed 325 days ago

Verified 415e40a3

metal : add FA-vec kernel for head size 64 (#13583)

ggerganov committed 325 days ago

Verified 654a6779

llama : print hint when loading a model when no backends are loaded (#13589)

slaren committed 325 days ago

Verified 5364ae4b

ci : add ppc64el to build-linux-cross (#13575)

CISC committed 325 days ago

Verified 7c07ac24

sycl : fixed compilation warnings (#13582)

lslusarczyk committed 326 days ago

Verified 0a338ed0

Merge remote-tracking branch 'origin/master' into tool-diffs

ochafik committed 326 days ago

6946a835

minja: sync (qwen3) (#13573)

ochafik committed 326 days ago

Verified bc098c3c

Merge remote-tracking branch 'origin/master' into tool-diffs

ochafik committed 326 days ago

d6e1d5bf

gguf : use ggml log system (#13571)

slaren committed 326 days ago

Verified c6a2c9e7

gguf-py : fix disconnect-before-connect in editor-gui (#13569)

danielzgtg committed 326 days ago

Verified 07ad2b6d

convert : fix conversion for llama 4 (#13567)

ngxson committed 326 days ago

Verified c531edfa

sycl: simplify bin_bcast_kernel (#13383)

AD2605 committed 326 days ago

Verified 02cdd2d8

sycl: reordered Q4_K MMVQ (#13109)

sgeor255 committed 326 days ago

Verified 64bb51cf

sycl: use oneDNN for matrices multiplication (#12972)

lslusarczyk committed 326 days ago

Verified 9c404ed5

llama-bench : fix -ot with dl backends (#13563)

slaren committed 326 days ago

Verified 6c8b9150

Newer Older