Release llamafile v0.8.6

Release llamafile v0.8.5

Release llamafile v0.8.4

Release llamafile v0.8.3

Release llamafile v0.8.2

- Upgrade to cosmocc 3.3.6
- Remove warnings from cuda build
- Fix bug in llamafile_trapping_enabled
- Refactor the new vectorized expf() code
- iqk_mul_mat() only needs codegen for AVX2
- Be less gung ho about the -ngl flag in README
- Restore shell scriptabiilty fix for new tokenizer
- Suppress divide by zero errors llama_print_timings()
- Cut back on tinyBLAS CPU multiple output type kernels
- Cut back NVIDIA fat binary releases to -arch=all-major
- Remove GA (won't rely on slow broken irregular cloud dev tools)
- Cut flash_attn_ext from release binaries (use --recompile to have it)

Release llamafile v0.8.1

Release llamafile v0.8

Release llamafile 0.7.4

Release llamafile v0.7.3

Release llamafile v0.7.2