Search results

Question about QJL abliation study

Status: Open.

#82 In TheTom/turboquant_plus;

· ryusaeba opened on Apr 16, 2026

time and performance overhead of quantization and dequantization

Status: Open.

#80 In TheTom/turboquant_plus;

· Szh1107 opened on Apr 13, 2026

Reproducibility of QJL resurrection issue

Status: Open.

#79 In TheTom/turboquant_plus;

· zhangsipeng opened on Apr 13, 2026

TurboFlash attention kernel: 13 GB excess Metal compute buffer allocation (commit 0d6b38aad)

Status: Open.

#77 In TheTom/turboquant_plus;

· shivam2014 opened on Apr 11, 2026

it run

Status: Open.

#74 In TheTom/turboquant_plus;

· ayttop opened on Apr 9, 2026

End-to-end inference test fails with --cache-type turbo4 on CPU

Status: Open.

#72 In TheTom/turboquant_plus;

· MELANCHOLY828 opened on Apr 9, 2026

Error when building from source

Status: Open.

#70 In TheTom/turboquant_plus;

· gabriel93blt opened on Apr 3, 2026

polar coordinate transformation operations

Status: Open.

#69 In TheTom/turboquant_plus;

· Keshawn082 opened on Apr 3, 2026

llama-quantize crashes with ios_base::failbit when using --tensor-type-file or --tensor-type (regression from #20503)

Status: Open.

#68 In TheTom/turboquant_plus;

· dogukanatakul opened on Apr 3, 2026

[Bug] Numerical instability (NaN/Infinite Loop) with Qwen 2.5/3.5 models using turbo4 on RTX 4070Ti

Status: Open.

#60 In TheTom/turboquant_plus;

· david01333 opened on Apr 1, 2026

Greetings from TurboQuant-MLX & Some Insights to Share! (System Prompt vs Boundary Layers)

Status: Open.

#59 In TheTom/turboquant_plus;

· helgklaizar opened on Apr 1, 2026

Unsupported gpu architecture 'compute_120a'

Status: Open.

#58 In TheTom/turboquant_plus;

· Ezzz-dev opened on Mar 31, 2026