[New Model][ROCm] Add AMD support for DeepSeek V4 (#40871)
Signed-off-by: ganyi <ygan@amd.com> Signed-off-by: whx-sjtu <xiaowang990929@gmail.com> Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com> Signed-off-by: tjtanaavllm <tunjian.tan@amd.com> Co-authored-by: ganyi <ygan@amd.com> Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com> Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
This commit is contained in:
co-authored by
ganyi
tjtanaa
tjtanaavllm
parent
2228fe6868
commit
628c436301
@@ -183,7 +183,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
|
||||
"int forced_token_heads_per_warp=-1) -> ()");
|
||||
ops.impl("fused_qk_norm_rope", torch::kCUDA, &fused_qk_norm_rope);
|
||||
|
||||
#ifndef USE_ROCM
|
||||
// Horizontally-fused DeepseekV4-MLA: per-head RMSNorm + GPT-J RoPE for Q, and
|
||||
// GPT-J RoPE + UE8M0 FP8 quant + paged cache insert for KV, all in one
|
||||
// kernel launch.
|
||||
@@ -194,7 +193,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
|
||||
"float eps, int cache_block_size) -> ()");
|
||||
ops.impl("fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert", torch::kCUDA,
|
||||
&fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert);
|
||||
#endif
|
||||
|
||||
// Apply repetition penalties to logits in-place
|
||||
ops.def(
|
||||
|
||||
Reference in New Issue
Block a user