|
|
7fff5fd39b
|
Fix: correct intermediate_size=3072, weight key prefix, dequantize shapes
|
2026-05-17 21:18:20 +00:00 |
|
|
|
4ef345773d
|
Rewrite pipeline test: load real weights, step-by-step vs BF16 reference
|
2026-05-17 21:17:18 +00:00 |
|
|
|
b43541afdd
|
Fix test path setup
|
2026-05-17 21:00:00 +00:00 |
|
|
|
490ddfa294
|
Pipeline test: use synthetic weights at 256x512 (JIT at 7168x18432 hangs for hours)
|
2026-05-17 20:58:06 +00:00 |
|
|
|
c1bb551446
|
Fix weight loading: skip already-loaded experts correctly
|
2026-05-17 18:15:51 +00:00 |
|
|
|
955d7533f2
|
Use system Python for pipeline test (CuTeDSL in system site-packages)
|
2026-05-17 18:13:42 +00:00 |
|
|
|
925e390b93
|
Fix import: use direct import from vllm/ subdirectory
|
2026-05-17 18:12:53 +00:00 |
|
|
|
cd6144b832
|
Fix imports: all functions are in cutedsl.bridge, not separate modules
|
2026-05-17 18:11:03 +00:00 |
|
|
|
5e63a0d8a3
|
Rewrite pipeline test: use raw checkpoint weights, compare runner vs dynamic-gs reference
|
2026-05-17 18:10:05 +00:00 |
|
|
|
e51eafe288
|
Rewrite pipeline test: compare runner vs reference with real weights, step-by-step
|
2026-05-17 18:08:33 +00:00 |
|
|
|
e38d60a6e8
|
Add pipeline test with real model weights, add swiglu_limit to reference moe_pipeline
|
2026-05-17 18:07:44 +00:00 |
|
