 AlpinDale
|
73177656ed
feat: quant_llm support (#755)
|
há 3 meses atrás |
|
AlpinDale
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
há 3 meses atrás |
|
AlpinDale
|
28b6397188
chore: quant config for speculative draft models (#719)
|
há 4 meses atrás |
|
AlpinDale
|
008e646c7e
chore: add support for up to 2048 block size (#715)
|
há 4 meses atrás |
|
AlpinDale
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
há 4 meses atrás |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
há 4 meses atrás |
|
AlpinDale
|
d5033e12fd
feat: implement mistral tokenizer mode (#711)
|
há 4 meses atrás |
|
AlpinDale
|
4fe371b7fa
fix: allow passing float for GiB arguments (#690)
|
há 4 meses atrás |
|
AlpinDale
|
bf88c8567e
feat: mamba model support (#674)
|
há 4 meses atrás |
|
AlpinDale
|
a0e446a17d
feat: initial encoder-decoder support with BART model (#633)
|
há 4 meses atrás |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
há 4 meses atrás |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
há 8 meses atrás |
|
AlpinDale
|
78d66f16d1
Chunked Prefill Part 1 (#384)
|
há 9 meses atrás |
|
AlpinDale
|
feb5840f2a
feat: async tokenization (#374)
|
há 9 meses atrás |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
há 9 meses atrás |
|
AlpinDale
|
c41462cfcd
feat: exllamav2 quantization (#305)
|
há 10 meses atrás |
|
AlpinDale
|
9810daa699
feat: INT8 KV Cache (#298)
|
há 10 meses atrás |
|
AlpinDale
|
e0c35bb353
feat: bitsandbytes and `--load-in{4,8}bit` support (#294)
|
há 10 meses atrás |
|
AlpinDale
|
705821a7fe
feat: AQLM quantization support (#293)
|
há 10 meses atrás |
|
AlpinDale
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
há 10 meses atrás |
|
AlpinDale
|
72229a94da
feat: better marlin kernels (#285)
|
há 10 meses atrás |
|
AlpinDale
|
657aec0cbd
refactor: OpenAI endpoint (#261)
|
há 10 meses atrás |
|
AlpinDale
|
4d04ade9ef
feat: fine-grained seeds (#279)
|
há 10 meses atrás |
|
AlpinDale
|
ea0f57b233
feat: allow further support for non-cuda devices (#247)
|
há 11 meses atrás |
|
AlpinDale
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
há 11 meses atrás |
|
AlpinDale
|
31c95011a6
feat: FP8 E5M2 KV Cache (#226)
|
há 11 meses atrás |
|
AlpinDale
|
641bb0f6e9
feat: add custom allreduce kernels (#224)
|
há 11 meses atrás |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
há 11 meses atrás |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
há 11 meses atrás |
|
AlpinDale
|
15a0454172
feat: FP8 KV Cache (#185)
|
há 1 ano atrás |
