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
2,917 workflow run results
2,917 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

sycl: flash-attention implementation Build on RISCV Linux Machine by Cloud-V #3448: Pull request #16969 synchronize by safranowith
10m 12s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
10m 12s
sycl: flash-attention implementation Build on RISCV Linux Machine by Cloud-V #3447: Pull request #16969 synchronize by safranowith
6m 38s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
6m 38s
readme : update hot topics Build on RISCV Linux Machine by Cloud-V #3446: Pull request #17002 opened by ggerganov
6m 43s ggerganov-patch-1
ggerganov-patch-1
6m 43s
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required Build on RISCV Linux Machine by Cloud-V #3444: Pull request #15248 synchronize by ExtReMLapin
12m 27s ExtReMLapin:fix_qwen_reasoning_tool_calling_required
ExtReMLapin:fix_qwen_reasoning_tool_calling_required
12m 27s
improve CUDA cpy memory bandwidth when copying transposed tensor Build on RISCV Linux Machine by Cloud-V #3443: Pull request #16841 synchronize by bssrdf
6m 55s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
6m 55s
ggml-hexagon: replace sprintf with snprintf in ops-utils.h Build on RISCV Linux Machine by Cloud-V #3442: Pull request #16913 synchronize by chraac
6m 40s chraac:dev-printf-opt
chraac:dev-printf-opt
6m 40s
improve CUDA cpy memory bandwidth when copying transposed tensor Build on RISCV Linux Machine by Cloud-V #3441: Pull request #16841 synchronize by bssrdf
6m 38s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
6m 38s
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required Build on RISCV Linux Machine by Cloud-V #3440: Pull request #15248 synchronize by ExtReMLapin
12m 10s ExtReMLapin:fix_qwen_reasoning_tool_calling_required
ExtReMLapin:fix_qwen_reasoning_tool_calling_required
12m 10s
server : do context shift only while generating Build on RISCV Linux Machine by Cloud-V #3439: Pull request #17000 opened by ggerganov
19m 56s gg/server-fix-ctx-shift-check
gg/server-fix-ctx-shift-check
19m 56s
Q4/Q8 Tiled Gemm Optimization. Build on RISCV Linux Machine by Cloud-V #3438: Pull request #16999 opened by shalinib-ibm
9m 23s shalinib-ibm:q8_q4_opt
shalinib-ibm:q8_q4_opt
9m 23s
CUDA: fix crash on uneven context Build on RISCV Linux Machine by Cloud-V #3437: Pull request #16988 synchronize by JohannesGaessler
10m 4s JohannesGaessler:cuda-fix-uneven-ctx
JohannesGaessler:cuda-fix-uneven-ctx
10m 4s
vulkan: Increase BK to 32; use BK/4 for non-CM mul_mm.comp Build on RISCV Linux Machine by Cloud-V #3436: Pull request #16636 reopened by SavicStefan
13m 53s SavicStefan:BK/4_and_BK=32
SavicStefan:BK/4_and_BK=32
13m 53s
vulkan: Increase BK to 32; use BK/4 for non-CM mul_mm.comp Build on RISCV Linux Machine by Cloud-V #3435: Pull request #16636 synchronize by SavicStefan
7m 25s SavicStefan:BK/4_and_BK=32
SavicStefan:BK/4_and_BK=32
7m 25s
vulkan: Increase BK to 32; use BK/4 for non-CM mul_mm.comp Build on RISCV Linux Machine by Cloud-V #3434: Pull request #16636 synchronize by SavicStefan
5m 3s SavicStefan:BK/4_and_BK=32
SavicStefan:BK/4_and_BK=32
5m 3s
fix: prevent data corruption when input==output in llama-quantize (#12753) Build on RISCV Linux Machine by Cloud-V #3433: Pull request #16997 synchronize by tamarPal
7m 3s tamarPal:fix-quantize-same-file-corruption
tamarPal:fix-quantize-same-file-corruption
7m 3s
fix: prevent data corruption when input==output in llama-quantize (#12753) Build on RISCV Linux Machine by Cloud-V #3432: Pull request #16997 synchronize by tamarPal
9m 38s tamarPal:fix-quantize-same-file-corruption
tamarPal:fix-quantize-same-file-corruption
9m 38s
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required Build on RISCV Linux Machine by Cloud-V #3431: Pull request #15248 synchronize by ExtReMLapin
8m 33s ExtReMLapin:fix_qwen_reasoning_tool_calling_required
ExtReMLapin:fix_qwen_reasoning_tool_calling_required
8m 33s
fix: prevent data corruption when input==output in llama-quantize (#12753) Build on RISCV Linux Machine by Cloud-V #3430: Pull request #16997 opened by tamarPal
15m 37s tamarPal:fix-quantize-same-file-corruption
tamarPal:fix-quantize-same-file-corruption
15m 37s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Build on RISCV Linux Machine by Cloud-V #3429: Pull request #16817 synchronize by GittyBurstein
21m 38s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
21m 38s
Model: add openPangu-Embedded Build on RISCV Linux Machine by Cloud-V #3428: Pull request #16941 synchronize by Lpzhan931
26m 48s Lpzhan931:feature/openpangu
Lpzhan931:feature/openpangu
26m 48s
improve CUDA cpy memory bandwidth when copying transposed tensor Build on RISCV Linux Machine by Cloud-V #3427: Pull request #16841 synchronize by bssrdf
33m 6s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
33m 6s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Build on RISCV Linux Machine by Cloud-V #3426: Pull request #16817 synchronize by GittyBurstein
7m 44s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
7m 44s
CUDA: add stream-based concurrency Build on RISCV Linux Machine by Cloud-V #3424: Pull request #16991 synchronize by am17an
31m 57s am17an:fused-qkv-stream
am17an:fused-qkv-stream
31m 57s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Build on RISCV Linux Machine by Cloud-V #3423: Pull request #16817 synchronize by GittyBurstein
32m 25s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
32m 25s
ci : apply model label to models Build on RISCV Linux Machine by Cloud-V #3422: Pull request #16994 opened by CISC
7m 3s cisc/ci-model-labeler
cisc/ci-model-labeler
7m 3s