Commit0828526

committed

Merge branch 'fix_pd_diff_tp' of github.com:ZhangGe6/TensorRT-LLM into fix_pd_diff_tp

Signed-off-by: Zhang Ge <sjtu.zg123@gmail.com>

2 parents28c9a32 +c135edb commit0828526Copy full SHA for 0828526

File tree

-1

lines changed

-1

lines changed

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -439,7 +439,7 @@ def test_attention_backend(s: Scenario):`
`439`	`439`	`s.max_num_pages,`
`440`	`440`	`2,`
`441`	`441`	`num_kv_heads,`
`442`		`-page_size,`
	`442`	`+page_size,`
`443`	`443`	`head_dim,`
`444`	`444`	`device="cuda").to(s.kvcache_dtype)`
`445`	`445`	`ref_kv_cache=flashinfer_kv_cache.transpose(1,2).contiguous().view(`

Comments

(0)