 Ho-Ren (Jack) Chuang
|
4b5f63e1b8
|
FIX: (NSA) Compute topk_indices_offset when NSA prefill flashmla_sparse is used with FP8 KV cache (#20606)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
|
2026-03-26 12:50:50 -07:00 |
|
|
Ho-Ren (Jack) Chuang
|
349ce2dd19
|
Support kv8 (FP8) with torch_native attention backend (#12596)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
|
2025-12-28 10:48:30 +08:00 |
|
|
Ho-Ren (Jack) Chuang
|
171b442ad3
|
Add KV4-capable backend flashmla and update server args (#14989)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
|
2025-12-12 11:50:27 -08:00 |
|
|
Ho-Ren (Jack) Chuang
|
10146af099
|
Check KV4 compatibility with attention backends and add KV4 support to the attention_backend doc (#14467)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
|
2025-12-11 19:00:53 -08:00 |
|
|
Ho-Ren (Jack) Chuang
|
3990b84bd3
|
Refactor MHA & MLA KV caches to support FP4 (#13547)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
|
2025-11-22 11:13:43 -08:00 |
|
|
Ho-Ren (Jack) ChuangandYichen Wang
|
6d5e16fb1c
|
feat: Add FP4 (E2M1) KV Cache Support for MHA (#12612)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
Co-authored-by: Yichen Wang <yichen.wang@bytedance.com>
|
2025-11-14 22:31:35 -08:00 |
|
|
Ho-Ren (Jack) ChuangandYichen Wang
|
76196b3cbf
|
feat: Add FP4 (E2M1) KV Cache Support with Quantization Utilities for MLA (#10078)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
Co-authored-by: Yichen Wang <yichen.wang@bytedance.com>
|
2025-11-01 22:24:58 -07:00 |
|