docs : replace typo "]"with ")" in README (#3179)
5e8b0f0
unverified
Alpaim
commited on
Spaces:
Sleeping
Sleeping
Commit History
whisper : remove redundant assignments (#3178)
ec40497
unverified
whisper : update CMakeLists.txt to handle deprecated gpu Warnings (#3163)
2ee9c36
unverified
Jugal Haresh Sheth
Jugal Sheth
commited on
ruby : add GGML_SYCL_DNN option to ruby bindings (#3172)
94d5ce3
unverified
talk-llama : sync llama.cpp
44ee199
sync : ggml
b16623d
CANN: Support MOE Model MUL_MAT_ID (llama/13042)
f013e2d
Chenguang Li
commited on
cmake: use the current build config for vulkan-shaders-gen (llama/13595)
7681e32
Gilad S.
commited on
vulkan: move common FA code to flash_attn_base.comp (llama/13556)
ad8b504
vulkan: use scalar FA rather than coopmat2 when N==1 (llama/13554)
97d9aa6
metal : add FA-vec kernel for head size 64 (llama/13583)
36a3b4e
sycl : fixed compilation warnings (llama/13582)
5037d84
Łukasz Ślusarczyk
commited on
gguf : use ggml log system (llama/13571)
a2211c9
Diego Devesa
commited on
sycl: simplify bin_bcast_kernel (llama/13383)
c39b646
Atharva Dubey
commited on
sycl: reordered Q4_K MMVQ (llama/13109)
6ca3a47
Svetlozar Georgiev
commited on
sycl: use oneDNN for matrices multiplication (llama/12972)
2008e08
Łukasz Ślusarczyk
commited on
arm64: optimize q6_k_q8_k kernel with i8mm (llama/13519)
03048ea
Yibo Cai
commited on
CUDA: fix crash on large batch size for quant. MoE (llama/13537)
df90a14
CUDA: faster Deepseek FA, add Turing support (llama/13435)
ace16dc
cmake: simplify vulkan shader test logic (llama/13263)
f8fd66d
bandoti
commited on
vulkan: KHR_coopmat flash attention (llama/13506)
4d1bd4f
vulkan: workaround FA compile failures on macos (llama/13517)
06833bc
metal : use FA-vec kernel up to batch size 20 (llama/13496)
e925f17
metal : optimize multi-sequence FA vec kernel (llama/13493)
d2f915d
ggml-cpu: Update KleidiAI to v1.6 and fix include directives (llama/13509)
7463545
Dan Johansson
commited on
mnist: fix segmentation fault (ggml/1227)
341f451
ggml : fix apple OS check in ggml_print_backtrace (ggml/1229)
5c0b540
Diego Devesa
commited on
ggml : Fix missing backtrace on Linux (ggml/1228)
82ee857
Daniel Tang
commited on
examples : add vad-speech-segments to win warns [no ci] (#3170)
90d9ecb
unverified
vad : return early if no vad segments are detected (#3158)
a28f11e
unverified
vad : store VAD context in whisper_state (#3156)
821d05f
unverified
whisper : add build_*/ to .gitignore [no ci] (#3157)
1374002
unverified
examples : add --print-confidence option to cli (#3150)
2d83266
unverified
vad : add download-vad-model scripts (#3149)
a40b758
unverified
server : add --flash-attn usage output (#3152)
8e966a8
unverified
talk-llama : sync llama.cpp
05d6d9c
whisper : update to ggml-backend changes (#0)
b12517c
sync : ggml
60acbd5
ggml : add mrope kernel for metal (llama/13457)
27b32e6
metal : optimize MoE for large batches (llama/13388)
d51c0d3
opencl: remove unnecessary assert for `add` (llama/13257)
a245fbf
lhez
commited on
llama/ggml: add LLM training support (llama/10544)
8d3b3c1
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel (llama/13053)
0612f1f
Dan Johansson
Charles Xu
commited on
CUDA: fix misaligned synchronization in FA (llama/13469)
40840d0
enable dpcpp nightly builds with libraries (llama/13406)
c9c1196
Atharva Dubey
commited on
CUDA: fix crash with partial offloading of MoE (llama/13439)
26820f6
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (llama/13386)
418769d
David Huang
commited on