v0.1.66-rc7

Pre-release candidate with native HQQ attention modes and release CI sidecar packaging fixes.

v0.1.66-rc6

Pre-release candidate with native HQQ attention modes, HQQ8 launcher default, HQQ4SC installer option, llama-witness sequence validation support, and release CI fixes for CUDA sidecars and Blackwell FLA sidecars.

v0.1.66-rc5

Pre-release candidate with native HQQ attention modes, HQQ8 launcher default, HQQ4SC installer option, llama-witness sequence validation support, and release CI fixes for CUDA sidecars and Blackwell FLA sidecars.

v0.1.66-rc4

Pre-release candidate with native HQQ attention modes, HQQ8 launcher default, HQQ4SC installer option, llama-witness sequence validation support, and release CI sidecar packaging fixes.

v0.1.66-rc3

Pre-release candidate with native HQQ attention modes, HQQ8 launcher default, HQQ4SC installer option, llama-witness sequence validation support, and release CI CUDA driver-stub linking fixes.

v0.1.66-rc2

Recreated rc2 on commit 418e3ce after switching the manylinux FLA link step to the resolved CUDA stub file path directly.

v0.1.66-rc1

Pre-release for multi-GPU testing.

Changes since v0.1.65-rc6:

• 122B FLA fix: multi-H cubins and scratch buffer sizing
• Cross-compiled FLA kernels for sm80/sm89/sm90/sm120
• FLA kernel arg signature and block size fix
• Arch-specific FLA .so files ship in wheel (no first-run JIT)
• GPU arch auto-detection with forward/backward compat fallback

v0.1.65-rc6

Prerelease for installed-package sidecar fixes and FP8-only KV cache on Ampere.

v0.1.65-rc5

Prerelease with vendored CUDA sidecars injected into release wheels, prerelease installer force-reinstall handling, and FP8-only KV cache on Ampere and in the interactive launcher.

v0.1.65-rc4

Prerelease with release-wheel sidecar injection, prerelease installer force-reinstall handling, and FP8-only KV cache on Ampere and in the interactive launcher.