[Quant] Use canonical N-first weight format for CT WNA16 MoE (#52798)

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: HDCharles <{"message":"Not Found","documentation_url":"https://docs.github.com/rest/users/emails#list-email-addresses-for-the-authenticated-user","status":"404"}>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
HDCharles
2026-09-28 11:22:44 -06:00
committed by GitHub
co-authored by Claude Opus 4.6 HDCharles <{"message":"Not Found","documentation_url":"https://docs.github.com/rest/users/emails#list-email-addresses-for-the-authenticated-user","status":"404"}> OpenAI Codex OpenAI Codex
parent 6d3ea3c2c9
commit c01368fd64
6 changed files with 222 additions and 209 deletions
+44 -9
View File
@@ -149,7 +149,11 @@ def test_wna16_oracle_rejects_incompatible_quant_structures(
assert expected in reason
def test_compressed_tensors_weights_are_transposed_for_triton():
def test_compressed_tensors_nfirst_weights_pass_through_for_triton():
"""CT provides N-first [E, N, K_packed] int32; Triton expects N-first uint8.
No transpose needed — just a view from int32 to uint8.
"""
quant_config = QuantizationArgs(
num_bits=4,
type=QuantizationType.INT,
@@ -158,10 +162,11 @@ def test_compressed_tensors_weights_are_transposed_for_triton():
dynamic=False,
group_size=32,
)
w13 = torch.arange(16, dtype=torch.int32).reshape(1, 2, 8)
w2 = torch.arange(12, dtype=torch.int32).reshape(1, 2, 6)
w13_scale = torch.arange(32, dtype=torch.float16).reshape(1, 4, 8)
w2_scale = torch.arange(18, dtype=torch.float16).reshape(1, 3, 6)
# N-first layout: [E, N, K_packed]
w13 = torch.arange(16, dtype=torch.int32).reshape(1, 8, 2)
w2 = torch.arange(12, dtype=torch.int32).reshape(1, 6, 2)
w13_scale = torch.arange(32, dtype=torch.float16).reshape(1, 8, 4)
w2_scale = torch.arange(18, dtype=torch.float16).reshape(1, 6, 3)
converted = convert_to_wna16_moe_kernel_format(
backend=WNA16MoEBackend.TRITON,
@@ -175,10 +180,40 @@ def test_compressed_tensors_weights_are_transposed_for_triton():
)
assert converted is not None
assert torch.equal(converted[0], w13.transpose(1, 2).contiguous().view(torch.uint8))
assert torch.equal(converted[1], w2.transpose(1, 2).contiguous().view(torch.uint8))
assert torch.equal(converted[2], w13_scale.transpose(1, 2).contiguous())
assert torch.equal(converted[3], w2_scale.transpose(1, 2).contiguous())
assert torch.equal(converted[0], w13.contiguous().view(torch.uint8))
assert torch.equal(converted[1], w2.contiguous().view(torch.uint8))
assert torch.equal(converted[2], w13_scale)
assert torch.equal(converted[3], w2_scale)
def test_gptq_nfirst_weights_pass_through_for_triton():
"""GPTQ frontend normalizes to N-first before calling oracle.
Verifies the oracle handles N-first GPTQ inputs the same way as CT.
"""
quant_config = AutoGPTQConfig(4, 128, False, True, False, {}, {})
# N-first layout (after GPTQ frontend transpose): [E, N, K_packed]
w13 = torch.arange(16, dtype=torch.int32).reshape(1, 8, 2)
w2 = torch.arange(12, dtype=torch.int32).reshape(1, 6, 2)
w13_scale = torch.arange(32, dtype=torch.float16).reshape(1, 8, 4)
w2_scale = torch.arange(18, dtype=torch.float16).reshape(1, 6, 3)
converted = convert_to_wna16_moe_kernel_format(
backend=WNA16MoEBackend.TRITON,
layer=torch.nn.Module(),
quant_config=quant_config,
input_dtype=None,
w13=w13,
w2=w2,
w13_scale=w13_scale,
w2_scale=w2_scale,
)
assert converted is not None
assert torch.equal(converted[0], w13.contiguous().view(torch.uint8))
assert torch.equal(converted[1], w2.contiguous().view(torch.uint8))
assert torch.equal(converted[2], w13_scale)
assert torch.equal(converted[3], w2_scale)
def test_moe_wna16_setup_forwards_selected_backend(monkeypatch):