[CI] Organize speculative decoding E2E tests by coverage (#50330)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Michael Goin
2026-07-31 18:05:42 -07:00
committed by GitHub
co-authored by OpenAI Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent b40d859c7b
commit fcdc7c2e9c
39 changed files with 1941 additions and 1863 deletions
+2 -2
View File
@@ -1449,8 +1449,8 @@ _SPECULATIVE_DECODING_EXAMPLE_MODELS = {
max_num_seqs=32,
),
"DFlashLagunaForCausalLM": _HfExamplesInfo(
"poolside/Laguna-XS-2.1",
speculative_model="poolside/Laguna-XS-2.1-DFlash",
"poolside/Laguna-XS-2.1-NVFP4",
speculative_model="poolside/Laguna-XS-2.1-DFlash-NVFP4",
use_original_num_layers=True,
max_model_len=8192, # Reduce max len to ensure test runs in low-VRAM CI env
max_num_seqs=32,