Skip to content

Actions: jamesburton/dotLLM

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
1,857 workflow runs
1,857 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
Hybrid CPU+GPU transformer: CPU-tail layers use neither per-layer SWA nor dense-YaRN RoPE Claude Code #991: Issue #432 opened by jamesburton
1s
1s
Hybrid CPU+GPU transformer: CPU-tail layers use neither per-layer SWA nor dense-YaRN RoPE Gemini Bot #991: Issue #432 opened by jamesburton
1s
1s
Vulkan RoPE ignores scaling config (YaRN) — dense attention long-context gap Claude Code #990: Issue #431 opened by jamesburton
1s
1s
Vulkan RoPE ignores scaling config (YaRN) — dense attention long-context gap Gemini Bot #990: Issue #431 opened by jamesburton
1s
1s
CUDA MLA (DeepSeek-V2/V3) RoPE ignores YaRN scaling — long-context correctness gap Gemini Bot #989: Issue #430 opened by jamesburton
1s
1s
CUDA MLA (DeepSeek-V2/V3) RoPE ignores YaRN scaling — long-context correctness gap Claude Code #989: Issue #430 opened by jamesburton
1s
1s
eval: sub-0.1% perplexity deltas are sequence artifacts — two deterministic harnesses disagree 5.7x on identical inputs Claude Code #988: Issue comment #429 (comment) created by jamesburton
1s
1s
eval: sub-0.1% perplexity deltas are sequence artifacts — two deterministic harnesses disagree 5.7x on identical inputs Gemini Bot #988: Issue comment #429 (comment) created by jamesburton
Skipped
Skipped
feat(eval): perplexity layer-select/offload plus a layer-cycling mode (#395) CI #201: Pull request #413 synchronize by jamesburton
7m 9s issue/395-perplexity-layer-offload-cycling
issue/395-perplexity-layer-offload-cycling
7m 9s
eval: sub-0.1% perplexity deltas are sequence artifacts — two deterministic harnesses disagree 5.7x on identical inputs Claude Code #987: Issue #429 opened by jamesburton
2s
2s
eval: sub-0.1% perplexity deltas are sequence artifacts — two deterministic harnesses disagree 5.7x on identical inputs Gemini Bot #987: Issue #429 opened by jamesburton
2s
2s
test(quant): IQ4_NL has no llama.cpp-transcription anchor — codebook interior is unpinned, and Nemotron GGUFs are ~91% IQ4_NL Gemini Bot #986: Issue #428 opened by jamesburton
1s
1s
test(quant): IQ4_NL has no llama.cpp-transcription anchor — codebook interior is unpinned, and Nemotron GGUFs are ~91% IQ4_NL Claude Code #986: Issue #428 opened by jamesburton
1s
1s
bug(vulkan): routed-bank F32 fallback reads a null f32Experts pointer for non-MLA quant-expert models (Q4_0/Q4_1/MXFP4) — silent corruption Claude Code #985: Issue #427 opened by jamesburton
1s
1s
bug(vulkan): routed-bank F32 fallback reads a null f32Experts pointer for non-MLA quant-expert models (Q4_0/Q4_1/MXFP4) — silent corruption Gemini Bot #985: Issue #427 opened by jamesburton
1s
1s
Vulkan MoE routed-bank device-resident coverage: add Q5_0 / IQ4_NL / Q2_K and make the F32-skip decision per bank instead of per model Claude Code #984: Issue comment #327 (comment) created by jamesburton
10s
10s
Vulkan MoE routed-bank device-resident coverage: add Q5_0 / IQ4_NL / Q2_K and make the F32-skip decision per bank instead of per model Gemini Bot #984: Issue comment #327 (comment) created by jamesburton
1s
1s
Vulkan DeepSeek MLA+MoE load OOMs with an unactionable OutOfMemoryException instead of preflighting the ~57 GB host F32 expert dequant Claude Code #983: Issue comment #326 (comment) created by jamesburton
12s
12s
Vulkan DeepSeek MLA+MoE load OOMs with an unactionable OutOfMemoryException instead of preflighting the ~57 GB host F32 expert dequant Gemini Bot #983: Issue comment #326 (comment) created by jamesburton
1s
1s
feat(eval): perplexity layer-select/offload plus a layer-cycling mode (#395) CI #200: Pull request #413 synchronize by jamesburton
5m 47s issue/395-perplexity-layer-offload-cycling
issue/395-perplexity-layer-offload-cycling
5m 47s
Running Copilot Code Review Copilot #113: by Copilot AI
3m 42s issue/407-moe-indexed-iq4nl-q5_0
issue/407-moe-indexed-iq4nl-q5_0
3m 42s
feat(vulkan): moe_indexed matmul for IQ4_NL and Q5_0 routed expert banks (#407) CI #199: Pull request #426 opened by jamesburton
6m 50s issue/407-moe-indexed-iq4nl-q5_0
issue/407-moe-indexed-iq4nl-q5_0
6m 50s
chore: three branches with unlanded work, open upstream issues and no PR (kvcache reserve-slot, tiled GEMM, skippable hardware tests) Gemini Bot #982: Issue #425 opened by jamesburton
9s
9s
chore: three branches with unlanded work, open upstream issues and no PR (kvcache reserve-slot, tiled GEMM, skippable hardware tests) Claude Code #982: Issue #425 opened by jamesburton
1s
1s
build: Microsoft.Build.Tasks.Git cannot read this repo's reftable ref storage — every local build errors Gemini Bot #981: Issue #424 opened by jamesburton
1s
1s