sm121/launcher @ 902e989c687809bd5ef2bf62a626dfd9442833cf

Alexander Korolev 902e989c68 r37 recipe: VLLM_MXFP8_LM_HEAD=0 - the lab tree's runtime LM-head MXFP8 quantization (default ON, absent from the eugr prod image) is the suspected cause of the typo regression		1 月之前
..
reports	5adc5325ff P2 result: R37 DS4.1 4x - 150/176 (85, safety-capped) but 3,830 pp = 2.3x prod prefill, TTFT 832 ms (2.1x better); reports landed (dev65-r37-ds41-4x)	1 月之前
recipe.toml	902e989c68 r37 recipe: VLLM_MXFP8_LM_HEAD=0 - the lab tree's runtime LM-head MXFP8 quantization (default ON, absent from the eugr prod image) is the suspected cause of the typo regression	1 月之前