Spaces:
Running
Running
Commit History
CUDA: remove bad assert (ggml/972)
91954a7
vulkan : multithread pipeline creation (ggml/963)
ba60f98
vulkan : fix build for GGML_VULKAN_RUN_TESTS, add TFLOPS to log (ggml/961)
85e2387
vulkan : argsort barriers must be under uniform control flow (ggml/951)
b2602d7
ggml : fix GGML_MAX_N_THREADS + improve formatting (ggml/969)
ad34655
server : ffmpeg overwrite leftover temp file (#2431)
2dafb8e
unverified
whisper : add large-v3-turbo (#2440)
f3283ba
unverified
tests : remove test-backend-ops (#2434)
050ba38
unverified
ci : disable failing CUDA and Java builds
ecef312
unverified
readme : fix references to download-ggml-model.sh (#2427)
3d92452
unverified
Hugo
commited on
make : remove "talk" target until updated
5fb8fce
ggml : add ggml-cpu-impl.h (skip) (#0)
958f2d3
sync : ggml
e22e2f8
talk-llama : sync llama.cpp
f91f98d
ggml : add AVX512DQ requirement for AVX512 builds (llama/9622)
14b5848
Eric Zhang
commited on
log : add CONT level for continuing previous log entry (llama/9610)
a29a4c5
threads: fix msvc build without openmp (llama/9615)
97b3eb5
Max Krasnyansky
commited on
cuda: add q8_0->f32 cpy operation (llama/9571)
6201c74
threads: improve ggml_barrier scaling with large number of threads (llama/9598)
aca04d5
Max Krasnyansky
commited on
ggml : AVX512 gemm for Q4_0_8_8 (llama/9532)
7349efc
metal : use F32 prec for K*Q in vec FA (llama/9595)
99c4239
Revert "[SYCL] fallback mmvq (ggml/9088)" (llama/9579)
5aceb3d
Akarshan Biswas
commited on
musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (llama/9526)
8ec75c3
R0CKSTAR
commited on
Fix merge error in #9454 (llama/9589)
3142fa9
CUDA: enable Gemma FA for HIP/Pascal (llama/9581)
97cb7ce
RWKV v6: RWKV_WKV op CUDA implementation (llama/9454)
8d3e707
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (llama/9573)
673df39
slaren
commited on
Update CUDA graph on scale change plus clear nodes/params (llama/9550)
6b63eb1
agray3
commited on
examples : adapt to ggml.h changes (ggml/0)
91c7734
ggml : refactoring (llama/#0)
1b62c96
ggml : fix builds (llama/0)
524a01b
ggml : fix trailing whitespace (llama/0)
214f95e
CUDA: fix sum.cu compilation for CUDA < 11.7 (llama/9562)
b305ecf
ggml : fix n_threads_cur initialization with one thread (llama/9538)
af82b69
slaren
Max Krasnyansky
commited on
threadpool : skip polling for unused threads (llama/9461)
9d11a7a
Max Krasnyansky
commited on
ggml : link MATH_LIBRARY not by its full path (llama/9339)
07d57ec
Michael Podvitskiy
commited on
cmake : do not hide GGML options + rename option (llama/9465)
8c32d36
ggml : IQ4_NL sgemm + Q4_0 AVX optimization (llama/9422)
f2986f6
Eve
commited on
metal : handle zero-sized allocs (llama/9466)
868283e
common : reimplement logging (llama/9418)
e893c97
cmake : correct order of sycl flags (llama/9497)
45ddbb5
Michael Podvitskiy
commited on
cmake : try to fix sycl+intel build (llama/9487)
dd66fc9
Michael Podvitskiy
commited on
ggml : ggml_type_name return "NONE" for invalid values (llama/9458)
8a1bb27
Yuri Khrustalev
commited on
cmake : use list(APPEND ...) instead of set() + dedup linker (llama/9463)
5497c27
cann: Add host buffer type for Ascend NPU (llama/9406)
7cbca42
Dou Xinpeng
commited on
riscv : modify Makefile and add a RISCV_VECT to print log info (llama/9442)
f77ad34
Ahmad Tameem
commited on
cann: Fix error when running a non-exist op (llama/9424)
74dcc66
Xinpeng Dou
commited on
CUDA: fix --split-mode row race condition (llama/9413)
b021272
musa: remove Clang builtins mapping (llama/9421)
ba2469d
R0CKSTAR
commited on