Skip to content

Actions: ggml-org/llama.cpp

Actions

Build on RISCV Linux Machine by Cloud-V

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build-riscv-native.yml
2,220 workflow runs
2,220 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

CUDA Copy Kernel for Contiguous Tensors for GGML CPY OP Build on RISCV Linux Machine by Cloud-V #2148: Pull request #16471 opened by anavp-nvidia
16m 4s anavp-nvidia:contiguous_cpy_cuda_kernel
anavp-nvidia:contiguous_cpy_cuda_kernel
16m 4s
vulkan: Add State Space Model (SSM) Operations Support Build on RISCV Linux Machine by Cloud-V #2147: Pull request #16463 synchronize by giuseppe
Action required giuseppe:ssm-vulkan
giuseppe:ssm-vulkan
Action required
model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules Build on RISCV Linux Machine by Cloud-V #2145: Pull request #16367 synchronize by sfallah
1h 6m 41s sfallah:embeddinggemma_sentence_transformers
sfallah:embeddinggemma_sentence_transformers
1h 6m 41s
opencl: add q8_0 mm support Build on RISCV Linux Machine by Cloud-V #2144: Pull request #16469 opened by lhez
1h 0m 55s CodeLinaro:q8_0-mm-lm
CodeLinaro:q8_0-mm-lm
1h 0m 55s
Implement llama-pull tool Build on RISCV Linux Machine by Cloud-V #2143: Pull request #16423 synchronize by ericcurtin
7h 35m 52s ericcurtin:llama-pull
ericcurtin:llama-pull
7h 35m 52s
ggml webgpu: profiling, CI updates, reworking of command submission Build on RISCV Linux Machine by Cloud-V #2141: Pull request #16452 synchronize by reeselevine
10h 25m 9s reeselevine:master
reeselevine:master
10h 25m 9s
ggml webgpu: profiling, CI updates, reworking of command submission Build on RISCV Linux Machine by Cloud-V #2140: Pull request #16452 synchronize by reeselevine
10h 33m 32s reeselevine:master
reeselevine:master
10h 33m 32s
ggml webgpu: profiling, CI updates, reworking of command submission Build on RISCV Linux Machine by Cloud-V #2139: Pull request #16452 synchronize by reeselevine
11h 4m 12s reeselevine:master
reeselevine:master
11h 4m 12s
ggml webgpu: profiling, CI updates, reworking of command submission Build on RISCV Linux Machine by Cloud-V #2138: Pull request #16452 synchronize by reeselevine
10h 54m 4s reeselevine:master
reeselevine:master
10h 54m 4s
ggml webgpu: profiling, CI updates, reworking of command submission Build on RISCV Linux Machine by Cloud-V #2137: Pull request #16452 synchronize by reeselevine
11h 0m 39s reeselevine:master
reeselevine:master
11h 0m 39s
ggml webgpu: profiling, CI updates, reworking of command submission Build on RISCV Linux Machine by Cloud-V #2136: Pull request #16452 synchronize by reeselevine
10h 59m 2s reeselevine:master
reeselevine:master
10h 59m 2s
server : Fixed canceling pending tasks Build on RISCV Linux Machine by Cloud-V #2135: Pull request #16467 opened by issixx
10m 16s issixx:fix-cancel-server-task
issixx:fix-cancel-server-task
10m 16s
llama : support LiquidAI LFM2-MoE hybrid model Build on RISCV Linux Machine by Cloud-V #2134: Pull request #16464 synchronize by tdakhran
9m 44s Liquid4All:tarek/feat/lfm2_moe
Liquid4All:tarek/feat/lfm2_moe
9m 44s
ggml-cpu: optimize the ggml NORM operation Build on RISCV Linux Machine by Cloud-V #2133: Pull request #15953 synchronize by duduta
9h 19m 46s duduta:optimize-ggml-cpu-norm
duduta:optimize-ggml-cpu-norm
9h 19m 46s
ggml-cpu: optimize the ggml NORM operation Build on RISCV Linux Machine by Cloud-V #2132: Pull request #15953 synchronize by duduta
Action required duduta:optimize-ggml-cpu-norm
duduta:optimize-ggml-cpu-norm
Action required
ggml-cpu: optimize the ggml NORM operation Build on RISCV Linux Machine by Cloud-V #2131: Pull request #15953 synchronize by duduta
Action required duduta:optimize-ggml-cpu-norm
duduta:optimize-ggml-cpu-norm
Action required
server : host-memory prompt caching Build on RISCV Linux Machine by Cloud-V #2130: Pull request #16391 synchronize by ggerganov
15m 52s gg/prompt-cache-ext
gg/prompt-cache-ext
15m 52s
ggml webgpu: profiling, CI updates, reworking of command submission Build on RISCV Linux Machine by Cloud-V #2129: Pull request #16452 synchronize by reeselevine
11m 44s reeselevine:master
reeselevine:master
11m 44s
llama : add normalized field to llama_token_data_array struct Build on RISCV Linux Machine by Cloud-V #2128: Pull request #16241 synchronize by danbev
6m 55s danbev:llama-token-data-one-value
danbev:llama-token-data-one-value
6m 55s
llama : support LiquidAI LFM2-MoE hybrid model Build on RISCV Linux Machine by Cloud-V #2127: Pull request #16464 synchronize by tdakhran
5m 58s Liquid4All:tarek/feat/lfm2_moe
Liquid4All:tarek/feat/lfm2_moe
5m 58s
server : host-memory prompt caching Build on RISCV Linux Machine by Cloud-V #2126: Pull request #16391 synchronize by ggerganov
39m 37s gg/prompt-cache-ext
gg/prompt-cache-ext
39m 37s
server : host-memory prompt caching Build on RISCV Linux Machine by Cloud-V #2125: Pull request #16391 synchronize by ggerganov
23m 5s gg/prompt-cache-ext
gg/prompt-cache-ext
23m 5s
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs Build on RISCV Linux Machine by Cloud-V #2124: Pull request #12063 synchronize by chraac
Action required chraac:dev-refactoring
chraac:dev-refactoring
Action required
llama : support LiquidAI LFM2-MoE hybrid model Build on RISCV Linux Machine by Cloud-V #2123: Pull request #16464 opened by tdakhran
13m 12s Liquid4All:tarek/feat/lfm2_moe
Liquid4All:tarek/feat/lfm2_moe
13m 12s
llama : add normalized field to llama_token_data_array struct Build on RISCV Linux Machine by Cloud-V #2122: Pull request #16241 synchronize by danbev
50m 28s danbev:llama-token-data-one-value
danbev:llama-token-data-one-value
50m 28s
ProTip! You can narrow down the results and go further in time using created:<2025-10-07 or the other filters available.