EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

mlapo add qdown output (#4707)

Browse Source 
### What this PR does / why we need it?
This PR adds mlapo operation support qdown of output.
### Does this PR introduce _any_ user-facing change?
mlapo operation add enable_inner_out of input
### How was this patch tested?
CI passed with new added/existing test.


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: h1074112368 <h1074112368@gmail.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
h1074112368
2025-12-06 11:18:53 +08:00
committed by GitHub
parent 8378f56f53
commit 74033999ed
8 changed files with 3136 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/mla_preprocess/op_kernel/mla_preprocess.h
View File

@@ -103,6 +103,9 @@ constexpr uint32_t KEY_FP16_CACHEMODE_1_QUANTMODE_0 = 1;
constexpr uint32_t KEY_BF16_CACHEMODE_0_QUANTMODE_0 = 256;
constexpr uint32_t KEY_BF16_CACHEMODE_1_QUANTMODE_0 = 257;
constexpr uint32_t KEY_BF16_CACHEMODE_3_QUANTMODE_0 = 259;
constexpr uint32_t KEY_BF16_CACHEMODE_0_QUANTMODE_0_INNER = 256 + 512;
constexpr uint32_t KEY_BF16_CACHEMODE_1_QUANTMODE_0_INNER = 257 + 512;
constexpr uint32_t KEY_BF16_CACHEMODE_3_QUANTMODE_0_INNER = 259 + 512;
enum class QuantMode : int32_t {
PER_TENSOR_ASYMM_QUANT = 0,