[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:
co-authored by
OpenAI Codex
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
b40d859c7b
commit
fcdc7c2e9c
@@ -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,
|
||||
|
||||
Reference in New Issue
Block a user