examples : add HEAPU8 to all of the exported runtime methods (#3134)
a4fc5fb
unverified
Enes Grahovac
commited on
Spaces:
Running
Running
Commit History
wasm : add note about worker.js file generation [no ci] (#3133)
c6a619d
unverified
whisper : deprecate WHISPER_CCACHE CMake option (#3131)
c4aa3ee
unverified
stream.wasm : add HEAPU8 to exported runtime methods (#3130)
df2c5e7
unverified
sync : ggml
87f0773
cuda : remove nrows_x in mul_mat_q_process_tile (llama/13325)
0fd6120
R0CKSTAR
commited on
CUDA: mix virt/real CUDA archs for GGML_NATIVE=OFF (llama/13135)
9fb68a1
SYCL: Disable reorder optimize by default and stop setting tensor extras when optimize is disabled (llama/13254)
53abb97
Akarshan Biswas
commited on
CUDA: fix bad asserts for partial offload (llama/13337)
23e676b
CUDA: fix --split-mode row for MMQ (llama/13323)
1136116
CUDA: fix logic for clearing padding with -ngl 0 (llama/13320)
c3e51a2
SYCL: Disable mul_mat kernels for noncontiguous tensor b (llama/13308)
3628417
Akarshan Biswas
commited on
rpc : use backend registry, support dl backends (llama/13304)
0286805
Diego Devesa
commited on
ggml : activate s390x simd for Q3_K (llama/13301)
1bfe279
CUDA: fix race condition in MMQ stream-k fixup (llama/13299)
160742f
CUDA: fix race condition in MMQ ids_dst (llama/13294)
d249810
vulkan: Additional type support for unary, binary, and copy (llama/13266)
b9cb11e
ci : add bindings-java jar artifact to release (#3126)
03b0716
unverified
cli : avoid std::exchange
ba2be5c
sync : ggml
27f99b0
vulkan : fix lint (llama/0)
49be727
ggml : Enable MMA for BF16 in llamafile_sgemm (llama/13148)
7da5bcc
rpc : avoid uninitialized memory in serialize_tensor (llama/13210)
31cad24
Justin Santa Barbara
commited on
ggml: Don't assert fail when tensor data changes (llama/13222)
af16d74
Jesse Gross
commited on
build : fix build info on windows (llama/13239)
415b9fc
Diego Devesa
commited on
vulkan: Add bfloat16 support (llama/12554)
b21f8a1
vulkan: Handle src1 batch dimension in non-contiguous mat-vec-mul shader (llama/13191)
710fdcf
vulkan : kernels for depthwise 2D convolution (CONV_2D_DW) (ggml/1204)
43d9f3e
ci : zip windows artifacts for release uploading (#3124)
3dbef6c
unverified
ci : add zip extension to xcframework artifact name (#3120)
a8a2519
unverified
whisper: remove MSVC warnings pragmas (#3090)
e0d130c
unverified
server: update abort mechanism to handle HTTP connection closure (#3112)
02b25fa
unverified
cli : support "-" for stdout like stdin (#3050)
7e3c27c
unverified
Daniel Tang
commited on
docs : Update cli documentation (#3102)
8566207
unverified
cmake : removed stdc++fs (#3097)
e715962
unverified
server : update httplib.h to version 0.20.0 (#3101)
238f652
unverified
ruby : refine HTTP cache feature (#3109)
f1d4a23
unverified
talk-llama : sync llama.cpp
05fda4a
sync : ggml
6d29e32
CUDA: batched+noncont MMQ, refactor bs>1 MoE code (llama/13199)
a867083
vulkan: use uint array index to avoid glslang bug (llama/13193)
fd2d86d
ggml : fix ppc64le build (llama/13176)
07ec79f
feat(ggml-cpu): enable z17 compile (llama/13182)
10f7d18
Aaron Teo
commited on
CUDA: fix non-cont. inputs for batched mat mul (llama/13155)
d13b876
fix(rpc): Improve input validation and error handling (llama/13069)
9e9f2fe
Ville Vesilehto
commited on
SYCL: Add all missing unary kernels (llama/13074)
d2ce872
Akarshan Biswas
commited on
musa: fix typo in cc control (llama/13144)
5fb7320
R0CKSTAR
commited on
CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (llama/13137)
e9c9d4b
musa: fix build warning (llama/13129)
3436ba4
R0CKSTAR
commited on
