Skip to content

Actions: ggerganov/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
7,708 workflow runs
7,708 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

save number of parameters and the size in llama_model, fixes #10285 Server #8094: Pull request #10286 synchronize by FirstTimeEZ
November 15, 2024 07:16 Action required FirstTimeEZ:patch-2
FirstTimeEZ:patch-2
November 15, 2024 07:16 Action required
server: (web UI) Add samplers sequence customization Server #8093: Pull request #10255 synchronize by MaggotHATE
November 15, 2024 04:28 8m 42s MaggotHATE:server-chat-templates
MaggotHATE:server-chat-templates
November 15, 2024 04:28 8m 42s
save number of parameters and the size in llama_model, fixes #10285 Server #8092: Pull request #10286 synchronize by FirstTimeEZ
November 15, 2024 03:47 Action required FirstTimeEZ:patch-2
FirstTimeEZ:patch-2
November 15, 2024 03:47 Action required
sycl: Use syclcompat::dp4a (#10267) Server #8091: Commit 5a54af4 pushed by airMeng
November 15, 2024 03:09 7m 39s master
master
November 15, 2024 03:09 7m 39s
vulkan: Optimize soft_max Server #8090: Pull request #10301 opened by jeffbolznv
November 15, 2024 02:37 17m 29s jeffbolznv:soft_max_opt
jeffbolznv:soft_max_opt
November 15, 2024 02:37 17m 29s
AVX BF16 and single scale quant optimizations Server #8089: Pull request #10212 synchronize by netrunnereve
November 15, 2024 01:10 13m 24s netrunnereve:avx_opt
netrunnereve:avx_opt
November 15, 2024 01:10 13m 24s
save number of parameters and the size in llama_model, fixes #10285 Server #8088: Pull request #10286 synchronize by FirstTimeEZ
November 15, 2024 00:47 Action required FirstTimeEZ:patch-2
FirstTimeEZ:patch-2
November 15, 2024 00:47 Action required
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921) Server #8087: Commit 1607a5e pushed by slaren
November 15, 2024 00:28 8m 17s master
master
November 15, 2024 00:28 8m 17s
save number of parameters and the size in llama_model, fixes #10285 Server #8086: Pull request #10286 synchronize by FirstTimeEZ
November 14, 2024 23:20 Action required FirstTimeEZ:patch-2
FirstTimeEZ:patch-2
November 14, 2024 23:20 Action required
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels Server #8085: Pull request #9921 synchronize by slaren
November 14, 2024 21:42 10m 24s chaxu01:feature/online-flow
chaxu01:feature/online-flow
November 14, 2024 21:42 10m 24s
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels Server #8084: Pull request #9921 synchronize by slaren
November 14, 2024 21:40 1m 56s chaxu01:feature/online-flow
chaxu01:feature/online-flow
November 14, 2024 21:40 1m 56s
vulkan: Optimize some mat-vec mul quant shaders Server #8083: Pull request #10296 opened by jeffbolznv
November 14, 2024 18:17 18m 55s jeffbolznv:mul_mat_vec_opt
jeffbolznv:mul_mat_vec_opt
November 14, 2024 18:17 18m 55s
Use smart pointers in simple-chat Server #8082: Pull request #10291 synchronize by ericcurtin
November 14, 2024 17:12 53m 53s ericcurtin:simple-chat-smart
ericcurtin:simple-chat-smart
November 14, 2024 17:12 53m 53s
ggml : build backends as libraries (#10256) Server #8081: Commit ae8de6d pushed by slaren
November 14, 2024 17:04 43m 47s master
master
November 14, 2024 17:04 43m 47s
Use smart pointers in simple-chat Server #8080: Pull request #10291 synchronize by ericcurtin
November 14, 2024 17:00 12m 6s ericcurtin:simple-chat-smart
ericcurtin:simple-chat-smart
November 14, 2024 17:00 12m 6s
Use smart pointers in simple-chat Server #8079: Pull request #10291 synchronize by ericcurtin
November 14, 2024 16:39 8m 16s ericcurtin:simple-chat-smart
ericcurtin:simple-chat-smart
November 14, 2024 16:39 8m 16s
Use smart pointers in simple-chat Server #8078: Pull request #10291 synchronize by ericcurtin
November 14, 2024 16:33 6m 19s ericcurtin:simple-chat-smart
ericcurtin:simple-chat-smart
November 14, 2024 16:33 6m 19s
Use smart pointers in simple-chat Server #8077: Pull request #10291 synchronize by ericcurtin
November 14, 2024 16:27 6m 28s ericcurtin:simple-chat-smart
ericcurtin:simple-chat-smart
November 14, 2024 16:27 6m 28s
Use smart pointers in simple-chat Server #8076: Pull request #10291 synchronize by ericcurtin
November 14, 2024 16:24 3m 13s ericcurtin:simple-chat-smart
ericcurtin:simple-chat-smart
November 14, 2024 16:24 3m 13s
ggml : build backends as libraries Server #8075: Pull request #10256 synchronize by slaren
November 14, 2024 15:24 9m 1s sl/dl-backend
sl/dl-backend
November 14, 2024 15:24 9m 1s
sycl: Add option to set the SYCL architecture for all targets Server #8074: Pull request #10266 synchronize by Rbiessy
November 14, 2024 15:23 20m 43s Rbiessy:romain/set_arch
Rbiessy:romain/set_arch
November 14, 2024 15:23 20m 43s
ggml : build backends as libraries Server #8073: Pull request #10256 synchronize by slaren
November 14, 2024 15:21 3m 30s sl/dl-backend
sl/dl-backend
November 14, 2024 15:21 3m 30s
sycl: Use syclcompat::dp4a Server #8072: Pull request #10267 synchronize by Rbiessy
November 14, 2024 15:13 14m 28s Rbiessy:romain/use_syclcompat_dp4a
Rbiessy:romain/use_syclcompat_dp4a
November 14, 2024 15:13 14m 28s
ggml: separate musa into its own section in the Makefile Server #8071: Pull request #10294 opened by yeahdongcn
November 14, 2024 14:55 7m 9s makllama:sl/dl-backend-musa-make
makllama:sl/dl-backend-musa-make
November 14, 2024 14:55 7m 9s
save number of parameters and the size in llama_model, fixes #10285 Server #8070: Pull request #10286 synchronize by FirstTimeEZ
November 14, 2024 14:36 Action required FirstTimeEZ:patch-2
FirstTimeEZ:patch-2
November 14, 2024 14:36 Action required