Skip to content

Actions: ggml-org/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
13,523 workflow runs
13,523 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Simplify and improve CUDA graphs through use of indirect copy pointers EditorConfig Checker #22697: Pull request #9017 synchronize by agray3
March 11, 2025 15:08 1h 20m 13s agray3:ag_indirect_copy_dest
agray3:ag_indirect_copy_dest
March 11, 2025 15:08 1h 20m 13s
vulkan: query register count and use it in a better split_k heuristic EditorConfig Checker #22696: Pull request #12319 synchronize by jeffbolznv
March 11, 2025 15:05 48m 30s jeffbolznv:pep_split_k
jeffbolznv:pep_split_k
March 11, 2025 15:05 48m 30s
sycl : variable sg_size support for mmvq kernels EditorConfig Checker #22695: Pull request #12336 opened by Alcpz
March 11, 2025 15:00 1h 13m 57s Alcpz:Alcpz/variable-sg-mmvq
Alcpz:Alcpz/variable-sg-mmvq
March 11, 2025 15:00 1h 13m 57s
vulkan: Add N/2 and N/4 optimized paths in coopmat2 shader EditorConfig Checker #22694: Pull request #12312 synchronize by jeffbolznv
March 11, 2025 14:59 59m 29s jeffbolznv:half_and_quarter_N
jeffbolznv:half_and_quarter_N
March 11, 2025 14:59 59m 29s
vulkan: use fp32 in coopmat2 q4_k dequant function EditorConfig Checker #22693: Pull request #12309 synchronize by jeffbolznv
March 11, 2025 14:52 54m 35s jeffbolznv:cm2_q4_k_fp32
jeffbolznv:cm2_q4_k_fp32
March 11, 2025 14:52 54m 35s
vulkan: Pad N dimension of B matrix for coopmat2 perf, to avoid bounds checking EditorConfig Checker #22692: Pull request #12273 synchronize by jeffbolznv
March 11, 2025 14:46 47m 47s jeffbolznv:pad_n_dimension
jeffbolznv:pad_n_dimension
March 11, 2025 14:46 47m 47s
vulkan: Adjust coopmat2 tile sizes and selection heuristic EditorConfig Checker #22691: Pull request #12258 synchronize by jeffbolznv
March 11, 2025 14:37 40m 6s jeffbolznv:coopmat2_tile_size
jeffbolznv:coopmat2_tile_size
March 11, 2025 14:37 40m 6s
bugfix: Respect n_predict=-2 in server (#12264) EditorConfig Checker #22690: Pull request #12323 synchronize by ishaangandhi
March 11, 2025 14:31 8m 4s ishaangandhi:respect-n_predict-2
ishaangandhi:respect-n_predict-2
March 11, 2025 14:31 8m 4s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #22689: Pull request #12326 synchronize by zhouwg
March 11, 2025 14:22 37m 42s kantv-ai:pr_to_upstream
kantv-ai:pr_to_upstream
March 11, 2025 14:22 37m 42s
vulkan: subgroup size tuning EditorConfig Checker #22687: Pull request #12087 synchronize by daniandtheweb
March 11, 2025 13:52 54m 16s daniandtheweb:rdna-subgroup-size
daniandtheweb:rdna-subgroup-size
March 11, 2025 13:52 54m 16s
server : improve infill stop criteria EditorConfig Checker #22686: Pull request #12333 opened by ggerganov
March 11, 2025 13:44 23m 52s gg/infill-better-stop
gg/infill-better-stop
March 11, 2025 13:44 23m 52s
ggml : fix quantized cpy op EditorConfig Checker #22685: Pull request #12310 synchronize by ggerganov
March 11, 2025 13:33 16m 29s gg/cpu-fix-cpy-q
gg/cpu-fix-cpy-q
March 11, 2025 13:33 16m 29s
ggml-backend : fix backend search path (#12330) EditorConfig Checker #22684: Commit ba76543 pushed by slaren
March 11, 2025 13:25 10m 13s master
master
March 11, 2025 13:25 10m 13s
Block interleaving support for Q4_K quantization for x86 AVX2 architecture EditorConfig Checker #22683: Pull request #12332 opened by Srihari-mcw
March 11, 2025 13:24 18s Srihari-mcw:q4k_block_interleaving
Srihari-mcw:q4k_block_interleaving
March 11, 2025 13:24 18s
Fix backend search path EditorConfig Checker #22682: Pull request #12330 synchronize by jklincn
March 11, 2025 12:36 20s jklincn:master
jklincn:master
March 11, 2025 12:36 20s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) EditorConfig Checker #22680: Pull request #12181 synchronize by ggerganov
March 11, 2025 11:54 19m 34s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
March 11, 2025 11:54 19m 34s
metal : Cache the Metal library at the device context level (#12265) EditorConfig Checker #22679: Commit 6ab2e47 pushed by ggerganov
March 11, 2025 11:45 4m 4s master
master
March 11, 2025 11:45 4m 4s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #22678: Pull request #12326 synchronize by zhouwg
March 11, 2025 11:44 25s kantv-ai:pr_to_upstream
kantv-ai:pr_to_upstream
March 11, 2025 11:44 25s
server: fix "--grammar-file" parameter EditorConfig Checker #22677: Pull request #12285 synchronize by dodekapod
March 11, 2025 11:24 42m 36s dodekapod:fix_grammar_file_in_server
dodekapod:fix_grammar_file_in_server
March 11, 2025 11:24 42m 36s
Allow s390x to load little endian models unmodified EditorConfig Checker #22676: Pull request #11234 synchronize by AlekseiNikiforovIBM
March 11, 2025 09:41 18s AlekseiNikiforovIBM:s390x_support
AlekseiNikiforovIBM:s390x_support
March 11, 2025 09:41 18s
Fixed Eval Bug: 12163 : Fallback to CPU when loading model: vk::PhysicalDevice::createDevice: ErrorExtensionNotPresent. EditorConfig Checker #22675: Pull request #12329 synchronize by ashwini778
March 11, 2025 09:10 Action required ashwini778:bugFix12163
ashwini778:bugFix12163
March 11, 2025 09:10 Action required
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #22674: Pull request #12326 synchronize by zhouwg
March 11, 2025 09:09 26s kantv-ai:pr_to_upstream
kantv-ai:pr_to_upstream
March 11, 2025 09:09 26s
Fixed Eval Bug: 12163 : Fallback to CPU when loading model: vk::PhysicalDevice::createDevice: ErrorExtensionNotPresent. EditorConfig Checker #22672: Pull request #12329 opened by ashwini778
March 11, 2025 08:44 Action required ashwini778:bugFix12163
ashwini778:bugFix12163
March 11, 2025 08:44 Action required
ggml : fix quantized cpy op EditorConfig Checker #22671: Pull request #12310 synchronize by ggerganov
March 11, 2025 08:39 9m 46s gg/cpu-fix-cpy-q
gg/cpu-fix-cpy-q
March 11, 2025 08:39 9m 46s
PR: Refine ggml-qnn backend(QNN, Qualcomm Neural Network,aka Qualcomm AI Engine Direct) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #22670: Pull request #12326 synchronize by zhouwg
March 11, 2025 08:27 9m 4s kantv-ai:pr_to_upstream
kantv-ai:pr_to_upstream
March 11, 2025 08:27 9m 4s