frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Build] Fix for the Wswitch-bool clang warning (#10060)

Browse Source 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
This commit is contained in:
Gregory Shtrasberg
2024-12-07 04:03:44 -05:00
committed by GitHub
parent 955fa9533a
commit f13cf9ad50
2 changed files with 8 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
csrc/attention/paged_attention_v1.cu
View File

@ -140,13 +140,10 @@ void paged_attention_v1_launcher(
blocksparse_block_size, blocksparse_head_sliding_step);
#define CALL_V1_LAUNCHER_SPARSITY(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE) \
switch (is_block_sparse) { \
case true: \
CALL_V1_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, true); \
break; \
case false: \
CALL_V1_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, false); \
break; \
if (is_block_sparse) { \
CALL_V1_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, true); \
} else { \
CALL_V1_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, false); \
}
// NOTE(woosuk): To reduce the compilation time, we omitted block sizes

11
csrc/attention/paged_attention_v2.cu
View File

@ -147,13 +147,10 @@ void paged_attention_v2_launcher(
blocksparse_head_sliding_step);
#define CALL_V2_LAUNCHER_SPARSITY(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE) \
switch (is_block_sparse) { \
case true: \
CALL_V2_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, true); \
break; \
case false: \
CALL_V2_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, false); \
break; \
if (is_block_sparse) { \
CALL_V2_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, true); \
} else { \
CALL_V2_LAUNCHER(T, CACHE_T, BLOCK_SIZE, IS_FP8_KV_CACHE, false); \
}
// NOTE(woosuk): To reduce the compilation time, we omitted block sizes