Spaces:
Running
Running
Commit History
whisper : make beam candidate sort more stable (#1943)
1316242
unverified
ggml : try fix 32-bit arm compat (#1938)
6ea3354
unverified
talk-llama : use llama_decode instead of llama_eval
301b000
unverified
talk-llama : sync llama.cpp
fe602cb
unverified
talk-llama : sync llama.cpp
802496b
unverified
sync : ggml
bad33a1
unverified
Revert "[SYCL] fix error when set main gpu to non-zero (llama/5901)" (llama/5918)
d7e8525
unverified
Neo Zhang Jianyu
commited on
fix error when set main gpu to non-zero (llama/5901)
829c347
unverified
Neo Zhang Jianyu
commited on
ggml : use SYS_get_cpu if SYS_getcpu is not defined (llama/5906)
909dbdc
unverified
ggml : use `uint8x16_t` return type for `ggml_vqtbl1q_u8` (llama/5894)
7f5bc53
unverified
bobqianic
commited on
add wait() to make code stable (llama/5895)
41c3c12
unverified
Neo Zhang Jianyu
commited on
quants : use MM256_SET_M128I consistently to fix gcc 7 build (llama/5889)
cdd783a
unverified
Vulkan Improvements (llama/5835)
ea2da45
unverified
fix mul_mat fault in CI/unit-test (llama/5862)
91bb65e
unverified
Neo Zhang Jianyu
jinliangtao
compilade
Cebtenzzre
Xuan Son Nguyen
ggerganov
HF Staff
Kawrakow
ikawrakow
Cebtenzzre
Michael Podvitskiy
phymbert
github-actions[bot]
Nindaleth
Black_Fox
iamlemec
slaren
dranger003
leejet
Minsoo Cheong
Dane Madsen
hutli
emozilla
commited on
jinliangtao
compilade
Cebtenzzre
Xuan Son Nguyen
ggerganov
HF Staff
Kawrakow
ikawrakow
Cebtenzzre
Michael Podvitskiy
phymbert
github-actions[bot]
Nindaleth
Black_Fox
iamlemec
slaren
dranger003
leejet
Minsoo Cheong
Dane Madsen
hutli
emozilla
commited on
ggml : fix unknown status (llama/0)
394e5d8
unverified
whisper : fix compute helper return (ggml/750)
b60b7f7
unverified
ggml : introduce ggml_status (ggml/750)
151c676
unverified
cuda : fix data race in soft max (llama/5853)
d1b60e4
unverified
slaren
commited on
ggml : fix IQ3_S AVX implementation (llama/5834)
98e5c63
unverified
ggml : IQ3_S improvements (llama/5829)
06a8e30
unverified
Support multiple GPUs (split mode) on SYCL backend (llama/5806)
b1865d2
unverified
Neo Zhang Jianyu
commited on
ggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was previously broken (llama/5813)
472195f
unverified
ddpasa
commited on
Use batched mul_mat pathway (llama/5591)
4a30367
unverified
AidanBeltonS
Abhilash Majumder
commited on
make portability_enumeration_ext apple only (llama/5757)
c164918
unverified
Eve
commited on
examples : Auto lowercase language parameter in main.cpp (#1928)
98b861a
unverified
F1L1P
bobqianic
commited on
examples : fix typo in bench.cpp (#1933)
8efe1fd
unverified
zhouwg
commited on
whisper : fix typo (#1925)
a0acef0
unverified
zhouwg
commited on
whisper.android.java : fix returns in JNI (#1929)
c1b258d
unverified
zhouwg
commited on
cmake : add library versioning (#1352)
3ab7ee7
unverified
readme : recommend MacOS Sonoma for Core ML (#1917)
c4e849b
unverified
Gavin Cai
commited on
talk-llama : sync llama.cpp
06c222c
unverified
sync : ggml
b85f30e
unverified
sync : llama.cpp (ggml/0)
8ea3a45
unverified
ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (llama/5760)
9a07f42
unverified
Attempt to fix android build (llama/5752)
e720b3b
unverified
IQ4_XS: a 4.25 bpw quantization (llama/5747)
0ee1bfb
unverified
cuda : replace remaining shfl_xor with calls to warp_reduce functions (llama/5744)
753b30d
unverified
Engininja2
commited on
ggml-quants : fix avx2 iq1_s vec_dot when compiled with gcc (llama/5742)
72e8610
unverified
Engininja2
commited on
CUDA: fix DEBUG_CUDA_MALLOC (llama/5729)
f18f386
unverified
Add support for soft_max ALiBi (llama/5639)
86d6a5e
unverified
AidanBeltonS
Abhilash Majumder
commited on
ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (llama/5711)
430efc6
unverified
add google magika inference example (ggml/748)
10ac4bb
unverified
slaren
commited on
stream.wasm : fix invalid memory access when no segments (#1902)
3273767
unverified
Andrew S
commited on