Skip to content

Actions: PrismML-Eng/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
cuda: gate (SwiGLU) fused PTQ1_0 mat-vec for 2-4 columns Server #452: Pull request #310 synchronize by sb32445
Action required sb32445:pr/ptq1-gate-up-fuse-mc
sb32445:pr/ptq1-gate-up-fuse-mc
Action required
cuda: gate (SwiGLU) fused PTQ1_0 mat-vec for 2-4 columns Pull Request Labeler #483: Pull request #310 synchronize by sb32445
21s
21s
cuda: prefetch the next PTQ1_0 mat-vec's weights into L2 from the last CTAs Server #451: Pull request #314 synchronize by sb32445
Action required sb32445:pr/ptq1-l2-prefetch
sb32445:pr/ptq1-l2-prefetch
Action required
cuda: prefetch the next PTQ1_0 mat-vec's weights into L2 from the last CTAs Pull Request Labeler #482: Pull request #314 synchronize by sb32445
14s
14s
cuda: use the MMA flash attention kernel for GQA above 4 with quantized K/V on Ada Server #450: Pull request #307 synchronize by sb32445
Action required sb32445:pr/fattn-gqa-mma
sb32445:pr/fattn-gqa-mma
Action required
cuda: use the MMA flash attention kernel for GQA above 4 with quantized K/V on Ada Pull Request Labeler #481: Pull request #307 synchronize by sb32445
24s
24s
Push on prism CodeQL #284: by bri-prism
22m 38s prism
prism
22m 38s
Push on prism CodeQL #283: by bri-prism
26m 25s prism
prism
26m 25s
speculative: enable prompt lookup for DFlash1 drafters Server #449: Pull request #334 opened by bri-prism
16m 9s perf/dflash1-prompt-lookup
perf/dflash1-prompt-lookup
16m 9s
speculative: enable prompt lookup for DFlash1 drafters Pull Request Labeler #480: Pull request #334 opened by bri-prism
25s
25s
PR #334 CodeQL #282: by bri-prism
9m 54s refs/pull/334/head
refs/pull/334/head
9m 54s
json-schema-to-grammar : convert empty anyOf / oneOf / type unions instead of emitting an empty rule flake8 Lint #114: Pull request #333 opened by professorpalmer
Action required professorpalmer:json-schema-empty-unions
professorpalmer:json-schema-empty-unions
Action required
json-schema-to-grammar : convert empty anyOf / oneOf / type unions instead of emitting an empty rule Python Type-Check #223: Pull request #333 opened by professorpalmer
Action required professorpalmer:json-schema-empty-unions
professorpalmer:json-schema-empty-unions
Action required
json-schema-to-grammar : convert empty anyOf / oneOf / type unions instead of emitting an empty rule Server #448: Pull request #333 opened by professorpalmer
Action required professorpalmer:json-schema-empty-unions
professorpalmer:json-schema-empty-unions
Action required
json-schema-to-grammar : convert empty anyOf / oneOf / type unions instead of emitting an empty rule Pull Request Labeler #479: Pull request #333 opened by professorpalmer
18s
18s
cuda: GGML_CUDA_FA_PREFILL_F16=N, f16 prefill for quantized K/V from pool memory (decode stays in place) Server #447: Pull request #330 opened by professorpalmer
Action required professorpalmer:claude/fa-prefill-f16-pool
professorpalmer:claude/fa-prefill-f16-pool
Action required
cuda: GGML_CUDA_FA_PREFILL_F16=N, f16 prefill for quantized K/V from pool memory (decode stays in place) Pull Request Labeler #478: Pull request #330 opened by professorpalmer
40s
40s
sycl: fuse the PQ2_0/PTQ1_0 XMX mat-muls with their neighbours (depends on #327) Server #446: Pull request #328 synchronize by kiljoy001
Action required kiljoy001:sycl-ternary-xmx-fusion
kiljoy001:sycl-ternary-xmx-fusion
Action required
sycl: PQ2_0/PTQ1_0 XMX kernels from TernSYCL, PTQ1_0 kept at 1.75 bpw Server #445: Pull request #327 synchronize by kiljoy001
Action required kiljoy001:sycl-ternary-xmx-ternsycl
kiljoy001:sycl-ternary-xmx-ternsycl
Action required
sycl: fuse the PQ2_0/PTQ1_0 XMX mat-muls with their neighbours (depends on #327) Pull Request Labeler #477: Pull request #328 synchronize by kiljoy001
16s
16s
sycl: PQ2_0/PTQ1_0 XMX kernels from TernSYCL, PTQ1_0 kept at 1.75 bpw Pull Request Labeler #476: Pull request #327 synchronize by kiljoy001
16s
16s
sycl: fuse the PQ2_0/PTQ1_0 XMX mat-muls with their neighbours (depends on #327) Server #444: Pull request #328 opened by kiljoy001
Action required kiljoy001:sycl-ternary-xmx-fusion
kiljoy001:sycl-ternary-xmx-fusion
Action required
sycl: fuse the PQ2_0/PTQ1_0 XMX mat-muls with their neighbours (depends on #327) Pull Request Labeler #475: Pull request #328 opened by kiljoy001
22s
22s
sycl: PQ2_0/PTQ1_0 XMX kernels from TernSYCL, PTQ1_0 kept at 1.75 bpw Server #443: Pull request #327 opened by kiljoy001
Action required kiljoy001:sycl-ternary-xmx-ternsycl
kiljoy001:sycl-ternary-xmx-ternsycl
Action required
sycl: PQ2_0/PTQ1_0 XMX kernels from TernSYCL, PTQ1_0 kept at 1.75 bpw Pull Request Labeler #474: Pull request #327 opened by kiljoy001
20s
20s