youkaichao 32176fee73 [torch.compile] support moe models (#9632) ...

Signed-off-by: youkaichao <youkaichao@gmail.com>

2024-10-27 21:58:04 -07:00

..

compressed_tensors

[torch.compile] support moe models (#9632)

2024-10-27 21:58:04 -07:00

kernels

[Kernel] Add Exllama as a backend for compressed-tensors (#9395)

2024-10-17 09:48:26 -04:00

utils

[Hardware][ROCM] using current_platform.is_rocm (#9642)

2024-10-28 04:07:00 +00:00

__init__.py

[Hardware][CPU] Support AWQ for CPU backend (#7515)

2024-10-09 10:28:08 -06:00

aqlm.py

[Kernel] fix types used in aqlm and ggml kernels to support dynamo (#7596)

2024-08-16 14:00:11 -07:00

awq_marlin.py

[torch.compile] support moe models (#9632)

2024-10-27 21:58:04 -07:00

awq_triton.py

[Kernel][Triton][AMD] Remove tl.atomic_add from awq_gemm_kernel, 2-5x speedup MI300, minor improvement for MI250 (#8646)

2024-09-21 09:20:54 +00:00

awq.py

[VLM] Enable overriding whether post layernorm is used in vision encoder + fix quant args (#9217)

2024-10-23 11:27:37 +00:00

base_config.py

[Core] Support loading GGUF model (#5191)

2024-08-05 17:54:23 -06:00

bitsandbytes.py

support bitsandbytes quantization with more models (#9148)

2024-10-08 19:52:19 -06:00

deepspeedfp.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

experts_int8.py

[Model] Adding support for MSFT Phi-3.5-MoE (#7729)

2024-08-30 13:42:57 -06:00

fbgemm_fp8.py

[Hardware][ROCM] using current_platform.is_rocm (#9642)

2024-10-28 04:07:00 +00:00

fp8.py

[Hardware][ROCM] using current_platform.is_rocm (#9642)

2024-10-28 04:07:00 +00:00

gguf.py

[Core] Refactor GGUF parameters packing and forwarding (#8859)

2024-10-07 10:01:46 +00:00

gptq_marlin_24.py

[Misc] Update gptq_marlin_24 to use vLLMParameters (#7762)

2024-08-26 17:44:54 -04:00

gptq_marlin.py

[torch.compile] support moe models (#9632)

2024-10-27 21:58:04 -07:00

gptq.py

[Kernel] Fullgraph and opcheck tests (#8479)

2024-09-25 08:35:52 -06:00

ipex_quant.py

[Hardware][CPU] Support AWQ for CPU backend (#7515)

2024-10-09 10:28:08 -06:00

kv_cache.py

[Bugfix] Fix kv_cache_dtype=fp8 without scales for FP8 checkpoints (#6761)

2024-07-25 09:46:15 -07:00

marlin.py

[Misc] Update marlin to use vLLMParameters (#7803)

2024-08-23 14:30:52 -04:00

modelopt.py

[Hardware][NV] Add support for ModelOpt static scaling checkpoints. (#6112)

2024-09-11 00:38:40 -04:00

neuron_quant.py

[Neuron] Adding support for adding/ overriding neuron configuration a… (#8062)

2024-09-04 16:33:43 -07:00

qqq.py

[Kernel] AQ AZP 3/4: Asymmetric quantization kernels (#7270)

2024-09-16 11:52:40 -07:00

schema.py

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)

2024-04-03 14:15:55 -07:00

tpu_int8.py

[misc] update tpu int8 to use new vLLM Parameters (#7973)

2024-08-29 16:46:55 -04:00