kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
3d0e38e074
TensorRT-LLMs/tensorrt_llm/_torch/modules
History
Void 6b755fd9f8
[None][fix] fix runtime error that bf16 input is not quantized to nvfp4 when use bf16 dispatch (#8507) 
Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
2025-10-30 15:06:54 +08:00
..
fla [None][feat] Support Qwen3 next (#7892) 2025-09-29 21:16:07 +08:00
fused_moe [None][fix] fix runtime error that bf16 input is not quantized to nvfp4 when use bf16 dispatch (#8507) 2025-10-30 15:06:54 +08:00
mamba [None][fix] enable NvFP4/FP8 quantization for Nemotron-H architecture (#7589) 2025-09-09 11:42:22 +03:00
__init__.py Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
attention.py [https://nvbugs/5550409][fix] Disable torch compile in piecewise attention part to Avoid host overhead (#8708) 2025-10-29 18:12:58 +08:00
decoder_layer.py chore: Change the type annotations of input_ids and position_ids to int32. (#4632) 2025-06-07 16:10:47 +08:00
embedding.py [None][feat] GPT-OSS Sm120/Sm121 Support (#7937) 2025-10-06 16:59:06 -04:00
gated_mlp.py [https://nvbugs/5505402] [fix] Disable deep_gemm for Qwen3 QKNormRoPEAttention and Linear layers due to accuracy issues (#7616) 2025-09-10 18:30:48 +01:00
layer_norm.py [TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405) 2025-10-24 13:40:41 -04:00
linear.py [https://nvbugs/5599086][fix] Fix FP8 Linear module for spark (#8707) 2025-10-29 13:58:19 -07:00
logits_processor.py feat: LogitsProcessor in PyTorch backend (#3145) 2025-05-01 14:15:30 -07:00
mlp.py feat: add LLmArgs option to force using dynamic quantization (#5346) 2025-07-01 12:16:09 -07:00
multi_stream_utils.py [None][refactor] Refactor Torch Compile Backend, MoeLoadBalancer and warmup Logic (#6615) 2025-08-19 09:58:44 +08:00
qk_norm_attention.py [None][fix] Avoid unnecessary concat in attn_output_gate case. (#8094) 2025-10-13 12:59:40 -07:00
rms_norm.py [None][chore] Refine qwen3-next implementation. (#8064) 2025-09-30 15:05:13 -04:00
rotary_embedding.py [TRTLLM-7385][feat] Optimize Qwen2/2.5-VL performance (#7250) 2025-09-22 03:40:02 -07:00
swiglu.py [None][chore] Wrap the swiglu into custom op to avoid redundant device copy. (#7021) 2025-08-27 13:02:10 +08:00
triton_linear.py [None] [feat] Add model gpt-oss (#6645) 2025-08-07 03:04:18 -04:00