304 kB

Ctrl+K

1 contributor

History: 30 commits

ticketguy

Test Lila end-to-end conversation

7baf037 verified 14 days ago

.gitattributes

1.52 kB
initial commit 16 days ago
README.md

734 Bytes
Update ML Intern artifact metadata 16 days ago
bench_full.py

11.1 kB
Full GPU benchmark including FP32 quant quality test 16 days ago
bench_train_only.py

7.3 kB
Training-only GPU benchmark (skip FP32 quant quality — already proven on CPU) 16 days ago
benchmark_gpu_fixed.py

10.9 kB
GPU benchmark script (fixed for PyTorch 2.11) 16 days ago
check_ui.py

1.25 kB
Check and fix mobile responsiveness 14 days ago
check_ui_responsive.py

1.99 kB
Check if Little Fig UI is mobile responsive 14 days ago
cleanup_repos.py

7.33 kB
Clean up repos: remove MIT references, remove Lila mentions, AGPL only 14 days ago
figquant_gpu_fixed.py

3.83 kB
FigQuant GPU training test (with dtype fix) 15 days ago
final_gpu_test.py

9.08 kB
Fix FigQuant GPU benchmark (use figcache mode) + test engine conversion 15 days ago
final_verify.py

11.3 kB
Verify and clarify novel contributions in paper + fix Colab 14 days ago
fix_all.py

7.8 kB
Fix lowram backward dtype bug + AGPL licenses + rerun GPU test 15 days ago
fix_colab_cloudflared.py

7.8 kB
Fix Colab: embed UI inline + use cloudflared tunnel (no auth needed) 14 days ago
fix_colab_install.py

2.82 kB
Fix Colab install: use [train] not [full], embers-diaries not on PyPI 14 days ago
fix_colab_no_ngrok.py

5.66 kB
Fix Colab: use Colab's native port output instead of ngrok 14 days ago
fix_colab_ui.py

5.27 kB
Fix Colab: spin up Little Fig Studio UI, not hardcoded training 14 days ago
fix_compile.py

5.86 kB
Fix engine compilation errors 15 days ago
fix_ui_mobile.py

5.1 kB
Make Little Fig Studio UI fully mobile responsive 14 days ago
kaggle_paper_and_memory.py

11.2 kB
CogMemBench paper for Kaggle + GPU memory reduction experiments 15 days ago
lila_engine_phase1.py

27.3 kB
Lila Engine Phase 1: Foundation — matmul kernel + model loader + token generation 16 days ago
lila_engine_phase1b.py

14.2 kB
Engine Phase 1b: AVX2 vectorized matmul + RMSNorm kernels 15 days ago
lila_engine_phase2.py

19.1 kB
Engine Phase 2: Full transformer forward pass + tokenizer + attention 15 days ago
lila_engine_phase3.py

28 kB
Engine Phase 3: Complete format converter + BPE tokenizer + kernel wiring 15 days ago
lila_engine_plan.py

20 kB
Lila inference engine build plan + fix LilaCore 16 days ago
lila_restructure.py

32.3 kB
Lila restructure script 16 days ago
memory_and_cogmem.py

9.31 kB
GPU memory experiment + CogMemBench on real model 15 days ago
memory_experiments.py

15.7 kB
Novel GPU memory reduction experiments 15 days ago
run_lila.py

2.01 kB
Test Lila end-to-end conversation 14 days ago
test_engine_compile.py

3.13 kB
Test engine compilation 15 days ago
update_docs.py

15.5 kB
Update paper + README with final GPU results, fix Colab, research GPU memory reduction 15 days ago