noonghunna
4d47d77fce
Prune dual vLLM composes: qwen-27b -> one config; gemma-31b default -> gemma-int8 (#279)
Settle the per-model dual vLLM set. qwen3.6-27b dual -> ONE (vllm/dual fp8 262K vision MTP); deprecate dual-dflash/dflash-noviz/tq3-nomtp/bf16/int8. gemma-4-31b dual -> keep TWO: DEFAULTS moved gemma-mtp -> gemma-int8 (full 262K + vision + 4 streams; rides v0.21.0+#40391 overlay), gemma-mtp kept as the stable v0.22.0 32K fallback. Registry entries kept (deprecated, not deleted) so patches.yml + hardware-gating tests stay valid. Out of scope: carnice/qwopus fine-tunes, gemma-26b-a4b, multi4. Suite 38/38.
2026-05-31 07:45:07 +05:00
..
2026-05-18 16:43:28 +00:00
2026-05-29 07:59:42 +05:00
2026-05-30 22:47:19 +05:00
2026-05-30 21:10:49 +05:00
2026-05-18 16:43:28 +00:00
2026-05-31 07:45:07 +05:00
2026-05-14 20:18:12 +00:00
2026-05-29 07:59:42 +05:00
2026-05-29 07:59:42 +05:00
2026-05-29 07:59:42 +05:00
2026-05-18 19:29:43 +00:00
2026-05-30 17:52:09 +05:00
2026-05-17 04:50:50 +00:00
2026-05-31 06:32:08 +05:00
2026-05-30 21:10:49 +05:00
2026-05-30 22:47:14 +05:00
2026-05-29 07:59:42 +05:00
2026-05-29 03:31:25 +05:00
2026-05-31 07:45:07 +05:00
2026-05-26 15:58:08 +00:00
2026-05-15 22:18:09 +05:00
2026-05-18 18:29:58 +00:00
2026-05-30 23:21:51 +05:00
2026-05-13 18:03:37 +00:00
2026-05-30 22:47:19 +05:00
2026-05-30 11:54:30 +05:00
2026-05-18 16:43:28 +00:00
2026-05-26 15:58:08 +00:00
2026-05-17 01:28:22 +00:00
2026-05-26 15:58:08 +00:00
2026-05-24 12:00:11 +00:00
2026-05-30 17:52:09 +05:00
2026-05-29 07:59:42 +05:00
2026-05-23 08:24:58 +05:00
2026-05-30 17:52:09 +05:00
2026-05-30 21:10:49 +05:00
2026-05-26 15:58:08 +00:00
2026-05-23 04:42:18 +00:00