 Po-Han Huang (NVIDIA)
|
bae29f716a
|
Fix inference mode mismatch in FlashInfer warmup (#33788)
|
2026-08-06 16:11:41 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
7eb27372b3
|
fix(server): capture legal multi-request prefill CUDA graph batches (#30206)
|
2026-08-03 16:56:59 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
5df193b4ac
|
[Speculative Decoding] Fix GPT-OSS EAGLE3 hidden states (#32334)
|
2026-07-31 11:58:49 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
5d004a20c5
|
Fix FlashInfer A2A top-k ID dtype (#29929)
|
2026-07-15 17:56:11 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
cfc3d0555e
|
Fix ModelOpt NVFP4 scalar scales for merged linears (#29151)
|
2026-07-13 16:14:20 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
17cce6a85f
|
Fix shared logits buffer for reduced-vocab draft models (#29943)
|
2026-07-02 16:08:56 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
72812db138
|
Avoid dynamic Q quantization in trtllm_mha (#29423)
|
2026-06-26 15:51:15 -07:00 |
|
|
Po-Han Huang (NVIDIA)andClaude Opus 4.6
|
ada52e5972
|
[Docs] Move ptxas sm_103a workaround into For CUDA 13 section (#22852)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-14 22:30:21 -07:00 |
|