Spaces:
Running
Running
Commit History
metal : support permuted matrix multiplicaions (llama/10033)
efb86a3
CUDA: fix insufficient buffer clearing for MMQ (llama/10032)
a41f94c
CUDA: fix MMQ for non-contiguous src0, add tests (llama/10021)
bcbaad3
increase cuda_cpy block size (ggml/996)
60f512e
metal : add POOL2D and fix IM2COL (llama/9943)
b553b89
Adapt to dynamically loadable backends mechanism (llama/9970)
f8d4728
leo-pony
commited on
ggml : add asserts for type conversion in fattn kernels (llama/9971)
9542e42
rpc : pack only RPC structs (llama/9959)
6bdbd69
fix mul_mat_vec_q and *_vec_q error (llama/9939)
691e6ac
Neo Zhang Jianyu
arthw
commited on
rpc : backend refactoring (llama/9912)
b6c412f
Add SYCL Backend registry, device and Event Interfaces (llama/9705)
f35cae5
Ouadie EL FAROUKI
commited on
add amx kernel for gemm (llama/8998)
db52137
vulkan : add backend registry / device interfaces (llama/9721)
df2cb6e
Diego Devesa
commited on
fix: allocating CPU buffer with size `0` (llama/9917)
ae9a15f
Gilad S
commited on
fix: use `vm_allocate` to allocate CPU backend buffer on macOS (llama/9875)
cf75979
Gilad S
commited on
CUDA: fix 1D im2col, add tests (ggml/993)
c24f7b1
Fix cann compilation error (llama/9891)
b480790
leo-pony
commited on
Vectorize load instructions in dmmv f16 CUDA kernel (llama/9816)
ddb0222
ggml : move more prints to the ggml log system (llama/9839)
98d1a6a
Diego Devesa
commited on
rpc : add backend registry / device interfaces (llama/9812)
4ac768e
Diego Devesa
commited on
musa: add docker image support (llama/9685)
553b278
R0CKSTAR
commited on
ggml : fix BLAS with unsupported types (llama/9775)
0a93e1b
Diego Devesa
commited on
ggml : add backend registry / device interfaces to BLAS backend (llama/9752)
7f269bb
Diego Devesa
commited on
Update building for Android (llama/9672)
27e2fca
Andrew Minh Nguyen
commited on
ggml : add metal backend registry / device (llama/9713)
b6adf19
metal : single allocation of encode_async block (llama/9747)
6e1b44c
ggml-alloc : remove buffer_id from leaf_alloc (ggml/987)
1a776cc
ggml : alloc ggml_contexts on the heap (#2525)
3ccf40a
unverified
vulkan : retry allocation with fallback flags (#2451)
9e91cbc
unverified
metal : zero-init buffer contexts (#0)
d651546
whisper : adapt to latest ggml (skip) (#0)
ad9dd7b
ggml : fix typo in example usage ggml_gallocr_new (ggml/984)
30a097b
ggml : fixes after sync (ggml/983)
237c05a
Diego Devesa
commited on
ggml-backend : add device and backend reg interfaces (llama/9707)
9d74d85
Diego Devesa
commited on
Fixed dequant precision issues in Q4_1 and Q5_1 (llama/9711)
5239c28
Ouadie EL FAROUKI
commited on
ggml-backend : add device and backend reg interfaces (llama/9707)
1bdb50a
Initial cmake support of SYCL for AMD GPUs (llama/9658)
7d7ac98
Alberto Cabrera Pérez
commited on
vulkan : do not use tensor->extra (llama/9407)
7d66a68
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
52069b8
ggml: refactor cross entropy loss CPU impl. (ggml/976)
2a0805f
metal : reduce command encoding overhead (llama/9698)
43d5a06
test: fix OPT_STEP_ADAMW for test-backend-ops (ggml/974)
76aa810
vulkan : mul_mat: fix UB with small warps (ggml/952)
d1a29c6
ggml : fix ggml_cast (ggml/973)
c44d575
ggml: fix gradient allocation logic (ggml/966)
ad3f29d
ggml : define missing HWCAP flags (llama/9684)
1d52105
ggml : add run-time detection of neon, i8mm and sve (llama/9331)
12c0e23
Dan Johansson
commited on
Enable use to the rebar feature to upload buffers to the device. (llama/9251)
760f8c2
Markus Tavenrath
commited on
mtgpu: enable VMM (llama/9597)
e84b4f5
R0CKSTAR
commited on