 kliuae
|
d80ddaac73
|
[ROCm][Perf] Kimi-K3 Store only the current rank's shards in latent MoE up-proj (#59591)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-10-08 14:55:20 +00:00 |
|
|
kliuae
|
0154979656
|
[ROCm][Perf] Kimi-K3 enable prefill checkpoints on ROCm (#58344)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-10-02 06:58:04 +00:00 |
|
|
kliuaeandNick Hill
|
7e583e615c
|
[Bugfix][Core] Fix mamba prefill checkpoint block reservation and prompt-end eviction in align mode (#59175)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-30 21:26:54 +00:00 |
|
|
|
9521c60bdc
|
[ROCm][Perf] Kimi-K3 Fused kernels for KDA prefill reland (#54038)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: kliuae <17350011+kliuae@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-09-10 15:37:54 +08:00 |
|
|
|
463aa5e30f
|
[ROCm][Perf] Kimi-K3 Fused kernels for KDA prefill (#52606)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-08-21 09:07:13 -07:00 |
|
|
kliuae
|
f96261637c
|
[ROCm][Perf] Kimi-K3 Remove prefill pipeline stall in chunk KDA (#51862)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-08-13 09:11:45 +00:00 |
|
|
|
7f9173dfa2
|
[ROCm][Perf] Kimi-K3 Fused kernel for KDA decode (#50654)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-08-11 20:39:34 -07:00 |
|
|
kliuae
|
43d691ec6b
|
[ROCm][Perf] Kimi-K3 Shard Latent MoE up-projection for ROCm path (#51253)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-08-07 06:11:18 +00:00 |
|
|
kliuae
|
f5cd862dbd
|
[ROCm][Bugfix] Kimi-K3 Fix KDA NaN on mixed batches and racy autotune config (#50649)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-08-05 08:07:21 +00:00 |
|
|
kliuaeandTJian
|
3c1bc1fc0d
|
[ROCm][Perf] Optimize sparse attention prefill kernel for DeepSeek-V4 (#48519)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-07-15 17:58:59 -07:00 |
|
|
kliuae
|
eb33ff34dd
|
[ROCm][Perf] DSv4 two-stage compressor kernel for HCA prefill (#47718)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-07-15 23:31:51 +00:00 |
|
|
kliuae
|
ab7521d77c
|
[ROCm][DSv4] Remove device pipeline stall in sparse attention (#43898)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-05-29 15:42:40 +08:00 |
|
|
|
a583c84e2b
|
[Bugfix][ROCm] Fix Accuracy Drop in Sparse Indexer on gfx950 (#43781)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2026-05-28 03:37:15 -07:00 |
|
|
kliuae
|
64f570ab56
|
[ROCm] [aiter] Split KV cache update for AiterFlashAttention (#33681)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-02-11 16:26:44 +00:00 |
|
|
kliuae
|
1c74150bca
|
[ROCm][CI] Fix "Distributed Tests (H200)" Test (#31227)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2025-12-24 06:56:30 +00:00 |
|
|
|
1317034379
|
[ROCm][FEAT] Fuse DeepSeek shared experts into AITER fused_moe ops (#24097)
Signed-off-by: chenjun <junchen2@amd.com>
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: valarLip <103567126+valarLip@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2025-10-16 10:41:34 +08:00 |
|
|
kliuae
|
c6cd5ca3d3
|
[ROCm][Bugfix] Fix compilation error in topk softmax fused kernel (#22819)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2025-08-13 13:45:03 -07:00 |
|
|
kliuae
|
ee659e3b60
|
[Bugfix][ROCm] Use chunked_prefill_paged_decode as fallback for V1 attention on ROCm (#18093)
Signed-off-by: kf <kuanfu.liu@embeddedllm.com>
|
2025-05-15 19:30:17 -07:00 |
|
|
|
5b794cae8d
|
[ROCm] Add aiter tkw1 kernel for Llama4 fp8 (#16727)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2025-04-21 20:42:34 -07:00 |
|
|
kliuae
|
7c25fe45a6
|
[AMD] Add support for GGUF quantization on ROCm (#10254)
|
2024-11-22 21:14:49 -08:00 |
|
|
kliuaeandmiloice
|
ff5abcd746
|
[ROCm] Add support for Punica kernels on AMD GPUs (#3140)
Co-authored-by: miloice <jeffaw99@hotmail.com>
|
2024-05-09 09:19:50 -07:00 |
|
|
kliuae
|
c9415c19d3
|
[ROCm] Fix warp and lane calculation in blockReduceSum (#3321)
|
2024-03-11 13:14:07 -07:00 |
|
|
kliuae
|
1b7c791d60
|
[ROCm] Fixes for GPTQ on ROCm (#2180)
|
2023-12-18 10:41:04 -08:00 |
|