Skip to content

Fix: resolve config mismatch in vllm_decode.py #4349

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
copybara-service merged 1 commit into from
Jul 6, 2026
+8 −26
Merged

Fix: resolve config mismatch in vllm_decode.py #4349

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 8 additions & 26 deletions src/maxtext/inference/vllm_decode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ def decode_with_vllm(config: Config) -> None:
"additional_config": {
"maxtext_config": {
"model_name": config.model_name,
"weight_dtype": config.weight_dtype,
"weight_dtype": config.weight_dtype.name,
"allow_split_physical_axes": True,
"debug_sharding": config.debug_sharding,
"prefuse_moe_weights": config.prefuse_moe_weights,
Expand Down Expand Up @@ -201,9 +201,7 @@ def decode_with_tunix(
overrides = config.vllm_hf_overrides
if isinstance(overrides, str) and "MaxTextForCausalLM" in overrides:
use_no_op_mappings = True
elif isinstance(overrides, dict) and "MaxTextForCausalLM" in overrides.get(
"architectures", []
):
elif isinstance(overrides, dict) and "MaxTextForCausalLM" in overrides.get("architectures", []):
use_no_op_mappings = True

tunix_model = TunixMaxTextAdapter(
Expand Down Expand Up @@ -238,19 +236,13 @@ def decode_with_tunix(
)

# MaxText uses -1 to mean "disabled"; vLLM requires top_p in (0, 1].
top_p = (
config.decode_sampling_nucleus_p
if config.decode_sampling_nucleus_p > 0
else 1.0
)
top_k = (
config.decode_sampling_top_k if config.decode_sampling_top_k > 0 else -1
)
top_p = config.decode_sampling_nucleus_p if config.decode_sampling_nucleus_p > 0 else 1.0
top_k = config.decode_sampling_top_k if config.decode_sampling_top_k > 0 else -1

rollout_vllm_additional_config = {
"maxtext_config": {
"model_name": config.model_name,
"weight_dtype": config.weight_dtype,
"weight_dtype": config.weight_dtype.name,
"allow_split_physical_axes": True,
"debug_sharding": config.debug_sharding,
"prefuse_moe_weights": config.prefuse_moe_weights,
Expand Down Expand Up @@ -280,17 +272,9 @@ def decode_with_tunix(
rollout_vllm_hbm_utilization=config.hbm_utilization_vllm,
rollout_vllm_init_with_random_weights=True,
rollout_vllm_tpu_backend_type="jax",
tensor_parallel_size=(
config.ici_tensor_parallelism
if config.ici_tensor_parallelism > 0
else 1
),
tensor_parallel_size=(config.ici_tensor_parallelism if config.ici_tensor_parallelism > 0 else 1),
data_parallel_size=jax.device_count()
// (
config.ici_tensor_parallelism
if config.ici_tensor_parallelism > 0
else 1
),
// (config.ici_tensor_parallelism if config.ici_tensor_parallelism > 0 else 1),
rollout_vllm_additional_config=rollout_vllm_additional_config,
rollout_vllm_kwargs={"hf_overrides": config.vllm_hf_overrides},
)
Expand Down Expand Up @@ -330,9 +314,7 @@ def main(argv: Sequence[str]) -> None:
if FLAGS.use_tunix:
maxtext_model, mesh = model_creation_utils.from_pretrained(config)
if config.lora.enable_lora:
maxtext_model = lora_utils.apply_lora_to_model(
maxtext_model, mesh, config
)
maxtext_model = lora_utils.apply_lora_to_model(maxtext_model, mesh, config)
if config.lora.lora_restore_path:
lora_utils.restore_lora_from_path(maxtext_model, config)
decode_with_tunix(config, model=maxtext_model, mesh=mesh)
Expand Down
Loading