|
About the qb Compiler category
|
|
0
|
37
|
February 25, 2026
|
|
Qbcompiler 1.4.0 지원 연산자 목록 관련
|
|
3
|
31
|
October 15, 2026
|
|
Qb Compiler rejects Llama-family models with `head_dim=160` ("View channel mismatch", `ch_gcd=3`)
|
|
2
|
73
|
October 8, 2026
|
|
Sam2 기반 모델 컴파일 관련 문의
|
|
2
|
133
|
September 18, 2026
|
|
[qb Compiler] Qwen3-0.6B (embedder + reranker) compiles succeed at `R1R2`/w8v8 but take ~22 hours each — is this expected, and can it be sped up?
|
|
4
|
35
|
September 18, 2026
|
|
[qb Compiler] backend="torch" combined mxq_compile() fails at device-allocation graph coloring for Qwen2.5-VL (OLMOCR2) — "some operators are missing during coloring"
|
|
1
|
53
|
September 16, 2026
|
|
[bug] python -m qbcompiler cannot produce the .mxq model
|
|
3
|
77
|
September 15, 2026
|
|
다중 입력 모델 컴파일 옵션 문의
|
|
1
|
29
|
September 8, 2026
|
|
Vlm 모델 컴파일 관련 문의
|
|
1
|
113
|
July 21, 2026
|
|
(MLA100 sdk) KV cache 지원 문의
|
|
3
|
122
|
July 20, 2026
|
|
배치 스케줄링 최적화를 위한 qbcompiler / qbruntime 내부 코드 수정 가능 여부 문의
|
|
1
|
121
|
July 6, 2026
|
|
EfficientViT always gives wrong predictions after MXQ compilation
|
|
2
|
128
|
June 12, 2026
|