sycl: fix example build (#2570)
a0dcffc
unverified
Stefan Sydow
commited on
Spaces:
Sleeping
Sleeping
Commit History
ci : use local ggml in Android build (#2567)
72b7501
unverified
ggml : tmp workaround for whisper.cpp (skip) (#2565)
ef26f48
unverified
update : readme
d1fa03c
unverified
scripts : fix sync path
9a2f912
unverified
whisper.swiftui : switch Mac dest to Mac (Designed for iPad) (#2562)
13f2beb
unverified
cmake : fix ppc64 check (#0)
f3c3fca
whisper : include ggml-cpu.h (#0)
cb35171
build : fixes
11d19cb
talk-llama : sync llama.cpp
6bb34fb
whisper : fix build (#0)
dfd316d
sync : ggml
9e83be6
sycl : Fixes to broken builds and test-backend-ops (llama/10257)
9cfb13b
Alberto Cabrera Pérez
commited on
vulkan: Optimize contiguous copies (llama/10254)
9974bd6
vulkan: Throttle the number of shader compiles during the build step. (llama/10222)
9677a2f
metal : more precise Q*K in FA vec kernel (llama/10247)
9160e8f
vulkan: Fix newly added tests for permuted mul_mat and 1D im2col (llama/10226)
76b8073
metal : reorder write loop in mul mat kernel + style (llama/10231)
661360d
metal : fix build and some more comments (llama/10229)
93fc215
metal : fix F32 accumulation in FA vec kernel (llama/10232)
228e0b2
metal : hide debug messages from normal log
efefcbb
ggml: fix zero division in ‘dne’ calculation in CUDA COUNT_EQUAL operator when ‘ne’ is small (#10213)
0ecc4d6
ggml : optimize llamafile cpu matrix multiplication for ppc64le (llama/10156)
18bdb35
amritahs-ibm
commited on
metal : opt-in compile flag for BF16 (llama/10218)
5f667d1
metal : improve clarity (minor) (llama/10171)
d68ae7c
metal : optimize FA kernels (llama/10171)
44ff932
ggml : add ggml-cpu.h to the public headers (llama/10204)
936a35f
Diego Devesa
commited on
fix q4_0_8_8 format for corrupted tokens issue (llama/10198)
4700b48
snadampal
EC2 Default User
commited on
metal : add BF16 support (llama/8439)
847669b
metal : fix from ptr buffer name (llama/10189)
c4d59b9
Diego Devesa
commited on
ggml : adjust is_first_call init value (llama/10193)
7e2b09b
metal : add quantized FA support (llama/10149)
f1ea157
ggml : fix arch check in bf16_to_fp32 (llama/10164)
09e4a9b
Diego Devesa
commited on
Q6_K AVX improvements (llama/10118)
b4c65b4
Eve
commited on
ggml : fix gelu tables initialization (llama/10172)
59dd404
Diego Devesa
commited on
ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (llama/10167)
ba20d5c
Diego Devesa
commited on
fix build break on arm64 linux (llama/10166)
68520c4
snadampal
commited on
cuda : clear error after changing peer access (llama/10153)
106cf6f
Diego Devesa
commited on
metal : simplify f16 and f32 dequant kernels (llama/0)
295521c
metal : move dequantize templates to beginning of MSL source (llama/0)
af0525c
CANN: adjust backend registry refactor. (llama/10158)
a0ecefd
leo-pony
commited on
ggml : move CPU backend to a separate file (llama/10144)
0f447f2
Diego Devesa
commited on
metal : minor fixup in FA kernel (llama/10143)
b6bfa42
llama : add simple-chat example (llama/10124)
41ff26f
Diego Devesa
Xuan Son Nguyen
commited on
llama : use smart pointers for ggml resources (llama/10117)
6b82135
Diego Devesa
commited on
vulkan : improve ggml_vk_create_buffer error handling (llama/9898)
2ce4d02
ggml : remove ggml_scratch (llama/10121)
3f0b7ba
build: fix build error in Windows env with OneAPI setup (llama/10107)
e295a3f
Zhenwei Jin
commited on
llama : fix buffer checks for mamba and rwk (llama/10111)
9df9767
Diego Devesa
commited on