 AlpinDale
|
7e72ce0a73
feat: mixtral tensor parallelism (#193)
|
преди 1 година |
|
AlpinDale
|
15a0454172
feat: FP8 KV Cache (#185)
|
преди 1 година |
|
AlpinDale
|
801eda0b7a
feat: support GPTQ 2, 3, and 8bit quants (#181)
|
преди 1 година |
|
AlpinDale
|
7c6fdea535
fix: GPTQ warnings and exllama states (#171)
|
преди 1 година |
|
AlpinDale
|
02f3ab3501
fix: replace head_mapping with num_kv_heads (#161)
|
преди 1 година |
|
AlpinDale
|
62b2c4119d
feat: re-write GPTQ and refactor exllama kernels (#152)
|
преди 1 година |
|
AlpinDale
|
1334a833a4
feat: AMD ROCm support (#95)
|
преди 1 година |
|
AlpinDale
|
2b1ba581f9
feat: re-implement GPTQ (#141)
|
преди 1 година |
|
AlpinDale
|
8223f85c1b
feat: SqueezeLLM support (#140)
|
преди 1 година |
|
AlpinDale
|
1aab8a7d6f
feat: speedup compilation times by 3x (#130)
|
преди 1 година |
