ggml-org/llama.cpp

Pull Requests Commits
imatrix : avoid using imatrix.dat in README
compilade committed 62 days ago
942c55cd
imatrix : avoid loading model to convert or combine imatrix
compilade committed 62 days ago
183eeb55
imatrix : warn when writing partial data, to help guess dataset coverage
compilade committed 62 days ago
50f53b3e
imatrix : add warning when legacy format is written
compilade committed 62 days ago
42423ec4
Merge branch 'master' into compilade/imatrix-batched-chunks
compilade committed 62 days ago
0ee322cd
tests : cover lfm2 cases in test_ssm_conv (#14651)
tdakhran committed 62 days ago
Verified c31e6064
docs : add LFM2 to models section (#14650)
tdakhran committed 62 days ago
Verified 67eade1b
CUDA: add set rows for f32 and f16 (#14551)
am17an committed 62 days ago
Verified 7de5c7ca
sync : ggml
ggerganov committed 62 days ago
8eff9554
vulkan : remove unused vars (#0)
ggerganov committed 62 days ago
3120413c
sync : ggml
ggerganov committed 62 days ago
21553570
vulkan : implement bilinear interpolation (ggml/1291)
Acly committed 62 days ago
74bb2945
vulkan : implement ggml_roll (ggml/1290)
Acly committed 62 days ago
3e303b11
server : fix pooled embedding output (#14645)
iamlemec committed 62 days ago
Verified 0c1df14b
vulkan: support SET_ROWS (#14587)
jeffbolznv committed 62 days ago
Verified b3ad3a01
vulkan: optimizations for deepseek prompt processing (#14555)
jeffbolznv committed 62 days ago
Verified 98197e5c
model : support LiquidAI LFM2 hybrid family (#14620)
tdakhran committed 63 days ago
Verified f5e96b36
HIP : Add HIP 7.0+ compatibility for hipBLAS compute types (#14634)
slojosic-amd committed 63 days ago
Verified 756aa102
readme : add hot PRs (#14636)
ggerganov committed 63 days ago
Verified aaa088d8
llama : move enum llama_vocab_pre_type to implementation (#14631)
ggerganov committed 63 days ago
Verified 0d5375d5
vocab : add midm-2.0 model pre-tokenizer (#14626)
Bing-su committed 63 days ago
Verified 576c82ed
model : Granite Four (#13550)
gabe-l-hart committed 63 days ago
Verified 0aedae00
opencl: add tiled mul_mat_f16_f32 (#14535)
rmatif committed 64 days ago
Verified 6bdda139
opencl: add `set_rows` for `f16` and `f32` (#14547)
lhez committed 64 days ago
Verified 0b885577
Smoldocling support (#14597)
ryan-mangeno committed 64 days ago
Verified 4bb625b7
Docs: script to auto-generate ggml operations docs (#14598)
am17an committed 64 days ago
Verified 11ee0fea
cmake : do not search for curl libraries by ourselves (#14613)
EZForever committed 64 days ago
Verified a4575513
SYCL: Initial set_rows kernel implementation (#14562)
qnixsynapse committed 64 days ago
Verified 704bb7a7
llama : minor coding style fix for smollm3 (#14605)
ngxson committed 64 days ago
Verified 435a6d10
cmake : bump llguidance version to v1.0.1 (#14609)
EZForever committed 64 days ago
Verified f9a867f5
Terms Of Use Privacy Policy Refund Policy Impressum