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
2,165 workflow run results
2,165 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

RVV1.0 Supported tests for RISC-V Build on RISCV Linux Machine by Cloud-V #2627: Pull request #16682 synchronize by alitariq4589
6m 42s alitariq4589:rvv1.0ci
alitariq4589:rvv1.0ci
6m 42s
RVV1.0 Supported tests for RISC-V Build on RISCV Linux Machine by Cloud-V #2626: Pull request #16682 opened by alitariq4589
5m 16s alitariq4589:rvv1.0ci
alitariq4589:rvv1.0ci
5m 16s
Fix: flush partial stop string when <EOG> is reached in /completion endpoint in streaming mode Build on RISCV Linux Machine by Cloud-V #2625: Pull request #15007 synchronize by matteoserva
3m 7s matteoserva:fix_stop_bug
matteoserva:fix_stop_bug
3m 7s
model : add BailingMoeV2 support Build on RISCV Linux Machine by Cloud-V #2624: Pull request #16063 synchronize by CISC
3m 4s cisc/bailingmoe2
cisc/bailingmoe2
3m 4s
metal : initial Metal4 tensor API support Build on RISCV Linux Machine by Cloud-V #2623: Pull request #16634 synchronize by ggerganov
3m 4s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
3m 4s
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required Build on RISCV Linux Machine by Cloud-V #2622: Pull request #15248 synchronize by ExtReMLapin
3m 6s ExtReMLapin:fix_qwen_reasoning_tool_calling_required
ExtReMLapin:fix_qwen_reasoning_tool_calling_required
3m 6s
ggml-alloc : fix leak when reusing a tensor with a larger size Build on RISCV Linux Machine by Cloud-V #2621: Pull request #16679 synchronize by slaren
7m 57s sl/fix-alloc-inline-leak
sl/fix-alloc-inline-leak
7m 57s
[RFC] vulkan: fix matmul pipeline selection for small n values Build on RISCV Linux Machine by Cloud-V #2620: Pull request #16681 opened by giuseppe
19m 40s giuseppe:change-selection-heuristic-mul_mat
giuseppe:change-selection-heuristic-mul_mat
19m 40s
extend server/public_simplechat with simple minded interactive browser-client side based toolcalling - base logic Build on RISCV Linux Machine by Cloud-V #2619: Pull request #16563 synchronize by hanishkvc
12m 55s hanishkvc:hkvc_server_simplechat_toolcalling_v0400
hanishkvc:hkvc_server_simplechat_toolcalling_v0400
12m 55s
Prevent premature submission on IME input Build on RISCV Linux Machine by Cloud-V #2618: Pull request #16673 synchronize by allozaur
15m 58s allozaur:16163-webui-sends-unfinished-query-on-IME-word-confirmation
allozaur:16163-webui-sends-unfinished-query-on-IME-word-confirmation
15m 58s
ggml-alloc : fix leak when reusing a tensor with a larger size Build on RISCV Linux Machine by Cloud-V #2617: Pull request #16679 opened by slaren
12m 39s sl/fix-alloc-inline-leak
sl/fix-alloc-inline-leak
12m 39s
Import/Export UX improvements Build on RISCV Linux Machine by Cloud-V #2616: Pull request #16619 synchronize by allozaur
25m 37s allozaur:allozaur/import-export-ux-improvements
allozaur:allozaur/import-export-ux-improvements
25m 37s
sycl: add PAD_REFLECT_D1 operator support Build on RISCV Linux Machine by Cloud-V #2615: Pull request #16145 synchronize by ye-NX
11m 46s ye-NX:ye/sycl-pad-reflect-d1
ye-NX:ye/sycl-pad-reflect-d1
11m 46s
graph : add clamping to ffn_moe_weights_sum to avoid div-by-zero Build on RISCV Linux Machine by Cloud-V #2613: Pull request #16655 synchronize by CISC
13m 18s cisc/norm-topk-bias
cisc/norm-topk-bias
13m 18s
sycl: add PAD_REFLECT_D1 operator support Build on RISCV Linux Machine by Cloud-V #2612: Pull request #16145 synchronize by ye-NX
10m 14s ye-NX:ye/sycl-pad-reflect-d1
ye-NX:ye/sycl-pad-reflect-d1
10m 14s
Enable per-conversation loading states to allow having parallel conversations Build on RISCV Linux Machine by Cloud-V #2611: Pull request #16327 synchronize by allozaur
7m 7s allozaur:16133-parallel-streaming
allozaur:16133-parallel-streaming
7m 7s
Enable per-conversation loading states to allow having parallel conversations Build on RISCV Linux Machine by Cloud-V #2610: Pull request #16327 synchronize by allozaur
7m 30s allozaur:16133-parallel-streaming
allozaur:16133-parallel-streaming
7m 30s
Enable per-conversation loading states to allow having parallel conversations Build on RISCV Linux Machine by Cloud-V #2609: Pull request #16327 synchronize by allozaur
16m 53s allozaur:16133-parallel-streaming
allozaur:16133-parallel-streaming
16m 53s
Import/Export UX improvements Build on RISCV Linux Machine by Cloud-V #2608: Pull request #16619 synchronize by allozaur
12m 14s allozaur:allozaur/import-export-ux-improvements
allozaur:allozaur/import-export-ux-improvements
12m 14s
Prevent premature submission on IME input Build on RISCV Linux Machine by Cloud-V #2607: Pull request #16673 synchronize by allozaur
12m 18s allozaur:16163-webui-sends-unfinished-query-on-IME-word-confirmation
allozaur:16163-webui-sends-unfinished-query-on-IME-word-confirmation
12m 18s
webui: introduce OpenAI-compatible model selector in JSON payload Build on RISCV Linux Machine by Cloud-V #2606: Pull request #16562 synchronize by ServeurpersoCom
19m 13s ServeurpersoCom:openai-model-selector
ServeurpersoCom:openai-model-selector
19m 13s
webui: introduce OpenAI-compatible model selector in JSON payload Build on RISCV Linux Machine by Cloud-V #2605: Pull request #16562 synchronize by ServeurpersoCom
5m 59s ServeurpersoCom:openai-model-selector
ServeurpersoCom:openai-model-selector
5m 59s
webui: introduce OpenAI-compatible model selector in JSON payload Build on RISCV Linux Machine by Cloud-V #2604: Pull request #16562 synchronize by ServeurpersoCom
16m 55s ServeurpersoCom:openai-model-selector
ServeurpersoCom:openai-model-selector
16m 55s
CUDA: fuse gate + up for mmvq, and mmvf Build on RISCV Linux Machine by Cloud-V #2603: Pull request #16630 synchronize by am17an
23m 18s am17an:cuda_fuse_gate
am17an:cuda_fuse_gate
23m 18s
webui: introduce OpenAI-compatible model selector in JSON payload Build on RISCV Linux Machine by Cloud-V #2602: Pull request #16562 synchronize by ServeurpersoCom
5m 58s ServeurpersoCom:openai-model-selector
ServeurpersoCom:openai-model-selector
5m 58s