Spaces:
Sleeping
Sleeping
Commit History
cuda : simplify expression
cda4a91
cuda : mark I16 and I32 ops as unsupported
cec288d
metal : add kernel_get_rows_i32
459dd87
metal : optimize ggml_mul_mat_id (faster Mixtral PP) (llama/4725)
8bc6274
metal : enable shader debugging (cmake option) (llama/4705)
7dd37dc
ggml : add ggml_vdotq_s32 alias (llama/4715)
96dc902
CUDA: fixed tensor cores not being used on RDNA3 (llama/4697)
654d245
CUDA: fix tensor core logic for Pascal and HIP (llama/4682)
977baeb
cuda: fix vmm oom issue on NVIDIA AGX Orin (llama/4687)
6980ee4
ggml : extend ggml_get_rows, ggml_repeat, ggml_concat (ggml/639)
f17d170
scripts : fix sync order + metal sed
1785412
examples : fix WASM Stack Overflow (#1713)
57c0e54
unverified
docker : fix the publishing of the CUDA Docker image (#1704)
6091193
unverified
bobqianic
commited on
scripts : do not sync commits from this repo
397f291
unverified
ci : build with CLBlast + ggml-opencl use GGML_API (#1576)
41a13d4
unverified
Tamotsu Takahashi
commited on
whisper : replace `tensor->n_dims` with `ggml_n_dims(tensor)` (#1694)
cee2822
unverified
bobqianic
commited on
sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691)
919a447
unverified
download : fix large q5 model name (#1695)
5df6c6c
unverified
whisper : Replace WHISPER_PRINT_DEBUG with WHISPER_LOG_DEBUG (#1681)
5ad04c9
unverified
bobqianic
commited on
sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)
aa86ade
unverified
docker : Dockerize whisper.cpp (#1674)
7163150
unverified
Chaoqun
commited on
CI : Add coverage for talk-llama when WHISPER_CUBLAS=1 (#1672)
983e4bd
unverified
bobqianic
commited on
examples : Revert CMakeLists.txt for talk-llama (#1669)
92a92ed
unverified
bobqianic
commited on
cmake : set default CUDA architectures (#1667)
0969db5
unverified
bobqianic
commited on
bench.py : add different large models (#1655)
282c3a3
unverified
Alfredo Montesinos
commited on
wchess : update README.md
8401568
unverified
release : v1.5.2
9dd774b
unverified
wchess : update readme
4b1cef7
unverified
wchess : whisper assisted chess (#1595)
6260b52
unverified
sync : ggml (Metal fixes, new ops, tests) (#1633)
a0d4b48
unverified
cmake : target windows 8 or above for prefetchVirtualMemory in llama-talk (#1617)
ed75714
unverified
Kreijstal
commited on
cmake : Fix bug in httplib.h for mingw (#1615)
334a75d
unverified
Kreijstal
commited on
metal : fix `ggml_metal_log` vargs (#1606)
b3cea90
unverified
whisper.objc : disable timestamps for real-time transcription
fc6989a
unverified
whisper : more debug messages + fix fallback logic
51d2d34
unverified
metal : fix soft_max kernel src1 argument (#1602)
5692844
unverified
sync : ggml (new ops, new backend, etc) (#1602)
895e87a
unverified
server : pass max-len argument to the server (#1574)
5704da9
unverified
ios : Remove `#if arch(arm)` check for using Metal (#1561)
3a600be
unverified
ggml : Fix 32-bit compiler warning (#1575)
3931068
unverified
Digipom
commited on
ggml : re-enable blas for src0 != F32 (#1583)
87987de
unverified
Server : Add support for .vtt format to Whisper server (#1578)
17f1f89
unverified
Aleksander Andrzejewski
commited on
server : backport .srt output format (#1565)
77aa181
unverified
Oleg Sidorov
commited on
cmake : install required ggml.h header (#1568)
9001318
unverified
Gregor Jasny
commited on
server : set default CORS headers to allow all (#1567)
531e483
unverified
Kasumi
commited on
readme : update help (#1560)
a5ad309
unverified
CI : Add CUDA 11.8.0 support (#1554)
8eaa345
unverified
bobqianic
commited on
CI : Rectify the Clang-Related workflow issues (#1551)
c093ec4
unverified
bobqianic
commited on