ochafik/llama.cpp

Pull Requests Commits

Revert "server: update webui to new reasoning_content diff"

ochafik committed 318 days ago

3ea2e7d1

Revert "update webui build"

ochafik committed 318 days ago

e9a0e2d0

update unit/test_tool_call.py::test_thoughts

ochafik committed 320 days ago

de81d4cf

update make_any_request in server test utils

ochafik committed 320 days ago

8faafcd7

update webui build

ochafik committed 320 days ago

abdb499e

server: update webui to new reasoning_content diff

ochafik committed 320 days ago

98acde2f

server: update deepseek reasoning format (now in reasoning_content diffs), add legacy option for compat

ochafik committed 320 days ago

961635c3

CUDA: fix typo in FlashAttention code (#13926)

JohannesGaessler committed 320 days ago

Verified e562eece

sched : avoid changing cur_copy when a graph is already allocated (#13922)

slaren committed 320 days ago

Verified b47ab7b8

parallel : increase the variability of the prompt lengths (#13927)

ggerganov committed 320 days ago

Verified dd665cc9

cuda : prevent using split buffers with 3d/4d matrices (#13919)

slaren committed 320 days ago

Verified df0c0c7d

SYCL: Add mrope kernel (#13755)

qnixsynapse committed 320 days ago

Verified b49a8ff9

sync : vendor (#13901)

ggerganov committed 320 days ago

Verified 53f92507

convert : fix rwkv bos/eos token (#13844)

CISC committed 320 days ago

Verified db38704f

convert : allow partial update to the chkhsh pre-tokenizer list (#13847)

ngxson committed 320 days ago

Verified 07e4351c

llama : add support for DistilBert (#13907)

huydt84 committed 320 days ago

Verified 291f2b69

llama : use llm_build_granite for minicpm (#13911)

zkh2016 committed 320 days ago

Verified 2c90da4c

cmake: Guard GGML_CPU_ALL_VARIANTS by architecture (#13890)

ckastner committed 321 days ago

Verified ec9e0301

llama : add support for jina-reranker-v2 (#13900)

CISC committed 321 days ago

Verified e83ba3e4

gguf-py : add support for sub_type (in arrays) in GGUFWriter add_key_value method (#13561)

CISC committed 321 days ago

Verified 2b131621

arm64: optimize q4_k_q8_k kernel with i8mm (#13886)

cyb70289 committed 321 days ago

Verified 54a2c7a8

cmake: Factor out CPU architecture detection (#13883)

ckastner committed 321 days ago

Verified 21fcc21a

ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (#13882)

vineelabhinav committed 321 days ago

Verified dd8ba934

tests : remove json.hpp from a test (#13880)

ggerganov committed 321 days ago

Verified 66c92061

convert : workaround for AutoConfig dummy labels (#13881)

CISC committed 321 days ago

Verified 5ca82fc1

llama : add RobertaForSequenceClassification reranker support (#13875)

CISC committed 322 days ago

Verified 6385b843

ggml: aarch64: Implement SVE F32 kernels for vector functions (#13843)

vineelabhinav committed 322 days ago

Verified 1b8fb815

gguf-py : fix SafetensorRemote return on undefined size (< 0) (#13841)

Beinsezii committed 322 days ago

Verified 53ae3064

llama : fix KV shift for qwen2vl (#13870)

ngxson committed 322 days ago

Verified 763d06ed

mtmd : move helpers to dedicated library (⚠️ breaking change) (#13866)

ngxson committed 322 days ago

Verified 10961339

Older