turboderp 97b0bbc5c0 Docs: Remove outdated quant duration estimates

2026-03-22 23:18:13 +01:00

..

cat.png

Initial commit

2025-04-06 14:42:49 +02:00

convert.md

Docs: Remove outdated quant duration estimates

2026-03-22 23:18:13 +01:00

cq_humaneval.png

Add cache quantization

2025-04-22 21:52:33 +02:00

exl3.md

Formatting

2025-04-06 15:08:25 +02:00

gumbel_eval.png

Initial commit

2025-04-06 14:42:49 +02:00

humaneval.png

Initial commit

2025-04-06 14:42:49 +02:00

llama31_8b_instruct_bpw.png

Initial commit

2025-04-06 14:42:49 +02:00

llama31_8b_instruct_kld_bpw.png

compare_q.py: Add KLD test and some other tweaks

2025-05-16 16:13:26 +02:00

llama31_8b_instruct_kld_vram.png

compare_q.py: Add KLD test and some other tweaks

2025-05-16 16:13:26 +02:00

llama31_8b_instruct_vram.png

Initial commit

2025-04-06 14:42:49 +02:00

llama31_70b_instruct_bpw.png

Initial commit

2025-04-06 14:42:49 +02:00

llama31_70b_instruct_vram.png

Initial commit

2025-04-06 14:42:49 +02:00

llama32_1b_instruct_bpw.png

Initial commit

2025-04-06 14:42:49 +02:00

llama32_1b_instruct_vram.png

Initial commit

2025-04-06 14:42:49 +02:00

mistral_7b_instruct_v0.3_bpw.png

Initial commit

2025-04-06 14:42:49 +02:00

mistral_7b_instruct_v0.3_vram.png

Initial commit

2025-04-06 14:42:49 +02:00

procedural_codebook.png

Initial commit

2025-04-06 14:42:49 +02:00