[MyPy] Fix mypy for vllm/lora (#41722)

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
This commit is contained in:
Martin Hickey
2026-06-22 10:57:09 -04:00
committed by GitHub
parent 1c7bc18318
commit ccd49f6821
15 changed files with 140 additions and 50 deletions
+11 -3
View File
@@ -111,19 +111,27 @@ def try_get_optimal_moe_lora_config(
# base MoE weight's block-wise quantization, so block_shape is omitted
# from the config lookup — the non-quantized branch in get_default_config
# ignores it anyway.
config = try_get_optimal_moe_config(w1_shape, w2_shape, top_k, dtype, M).copy()
raw_config = try_get_optimal_moe_config(w1_shape, w2_shape, top_k, dtype, M)
config: dict[str, int | None] = dict(raw_config)
if op_type in [
"fused_moe_lora_w13_shrink",
"fused_moe_lora_w2_shrink",
]:
block_size_n = config.get("BLOCK_SIZE_N")
config["BLOCK_SIZE_N"] = min(
config.get("BLOCK_SIZE_N", 64), next_power_of_2(rank)
block_size_n if block_size_n is not None else 64,
next_power_of_2(rank),
)
elif op_type in [
"fused_moe_lora_w13_expand",
"fused_moe_lora_w2_expand",
]:
block_size_k = config.get("BLOCK_SIZE_K")
config["BLOCK_SIZE_K"] = max(
16, min(config.get("BLOCK_SIZE_K", 32), next_power_of_2(rank))
16,
min(
block_size_k if block_size_k is not None else 32,
next_power_of_2(rank),
),
)
return config