 Georgi Gerganov
|
fab647e884
server : add cache reuse card link to help (#13230)
|
8 months ago |
 Xuan-Son Nguyen
|
dcf886007d
convert : explicitly disable trust_remote_code for AutoConfig (#13246)
|
8 months ago |
 bandoti
|
d24d592808
ci: fix cross-compile sync issues (#12804)
|
8 months ago |
 Justin Santa Barbara
|
8efbdadc61
rpc : avoid uninitialized memory in serialize_tensor (#13210)
|
8 months ago |
 Jesse Gross
|
f057808ffa
ggml: Don't assert fail when tensor data changes (#13222)
|
8 months ago |
 Diego Devesa
|
d7a14c42a1
build : fix build info on windows (#13239)
|
8 months ago |
 Loïc Carrère
|
b6e4ff69b8
clip : (minicpmv) Re-enable upscaling of images smaller than the CLIP image size (#13237)
|
8 months ago |
 matteo
|
e0f572c846
llama-chat : update GLM4 chat template (#13238)
|
8 months ago |
 Jeff Bolz
|
79f26e9e12
vulkan: Add bfloat16 support (#12554)
|
8 months ago |
|
Jeff Bolz
|
fc727bcdd5
vulkan: Handle src1 batch dimension in non-contiguous mat-vec-mul shader (#13191)
|
8 months ago |
 Johannes Gäßler
|
b0ecbd434b
test: non-cont. b in test-backend-ops -o MUL_MAT (#13187)
|
8 months ago |
|
Georgi Gerganov
|
b1dd4d08e8
sync : ggml
|
8 months ago |
 Daniel Bevenius
|
99881f77d8
whisper : add check that target name exists (whisper/3103)
|
8 months ago |
|
Daniel Bevenius
|
b5769d92b4
ggml : suppress Windows compiler warnings (whisper/3075)
|
8 months ago |
|
Xuan-Son Nguyen
|
8936784f7a
mtmd : add **vision** support for Mistral Small 3.1 (#13231)
|
8 months ago |
|
Xuan-Son Nguyen
|
13c9a3319b
arg : remove CURLINFO_EFFECTIVE_METHOD (#13228)
|
8 months ago |
 Jared Van Bortel
|
a70183eb00
llama-model : fix the reported size class for nomic-embed-text-v2-moe (#13223)
|
8 months ago |
|
Georgi Gerganov
|
8d33d740c3
sync : ggml
|
8 months ago |
|
Diego Devesa
|
4254bb4951
ggml : fix ggml_gallocr_ptr type (ggml/1205)
|
8 months ago |
|
Georgi Gerganov
|
9998540149
cuda : fix unused variable compile warning (whisper/0)
|
9 months ago |
|
Johannes Gäßler
|
e1e8e0991f
CUDA: batched+noncont MMQ, refactor bs>1 MoE code (#13199)
|
8 months ago |
|
Xuan-Son Nguyen
|
6f67cf1f48
arg : -hf do not fail if url mismatch (#13219)
|
8 months ago |
 ddh0
|
16a457facd
fix typo: `n_ctx_pre_seq` -> `n_ctx_per_seq` (#13221)
|
8 months ago |
|
Xuan-Son Nguyen
|
3e168bede4
convert : improve model arch handling (#13122)
|
8 months ago |
 Tatsuya Tanaka
|
ceda28ef8e
llava : remove duplicate include (#13207)
|
8 months ago |
 Olivier Chafik
|
3b127c7385
common : add -jf / --json-schema-file flag (#12011)
|
8 months ago |
|
Jeff Bolz
|
e5007a5edf
vulkan: use uint array index to avoid glslang bug (#13193)
|
8 months ago |
 shalinib-ibm
|
416313773b
ggml : fix ppc64le build (#13176)
|
8 months ago |
|
Xuan-Son Nguyen
|
07c2e2f76c
convert : correct typo image_mean --> image_std (#13208)
|
8 months ago |
 Aaron Teo
|
44cd8d91ff
feat(ggml-cpu): enable z17 compile (#13182)
|
8 months ago |
