* llama : add pipeline parallelism support for batch processing with multiple CUDA GPUs ggml-ci * server : add -ub, --ubatch-size parameter * fix server embedding test * llama : fix Mamba inference for pipeline parallelism Tested to work correctly with both `main` and `parallel` examples. * llama : limit max batch size to n_batch * add LLAMA_SCHED_MAX_COPIES to configure the number of input copies for pipeline parallelism default increase to 4 (from 2) changing this value may improve performance for some systems, but increases memory usage * fix hip build * fix sycl build (disable cpy_tensor_async) * fix hip build * llama : limit n_batch and n_ubatch to n_ctx during context creation * llama : fix norm backend * batched-bench : sync after decode * swiftui : sync after decode * ggml : allow ggml_get_rows to use multiple threads if they are available * check n_ubatch >= n_tokens with non-casual attention * llama : do not limit n_batch to n_ctx with non-casual attn * server : construct batch with size of llama_n_batch * ggml_backend_cpu_graph_compute : fix return value when alloc fails * llama : better n_batch and n_ubatch comment * fix merge * small fix * reduce default n_batch to 2048 --------- Co-authored-by: Francis Couture-Harpin <git@compilade.net> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> |
||
---|---|---|
.. | ||
CMakeLists.txt | ||
perplexity.cpp | ||
README.md |
perplexity
TODO
Llama 2 70B Scorechart
Quantization | Model size (GiB) | Perplexity | Delta to fp16 |
---|---|---|---|
Q4_0 | 36.20 | 3.5550 | 3.61% |
Q4_1 | 40.20 | 3.5125 | 2.37% |
Q5_0 | 44.20 | 3.4744 | 1.26% |
Q2_K | 27.27 | 3.7339 | 8.82% |
Q3_K_S | 27.86 | 3.7019 | 7.89% |
Q3_K_M | 30.83 | 3.5932 | 4.72% |
Q3_K_L | 33.67 | 3.5617 | 3.80% |
Q4_K_S | 36.39 | 3.4852 | 1.57% |
Q4_K_M | 38.54 | 3.4725 | 1.20% |
Q5_K_S | 44.20 | 3.4483 | 0.50% |
Q5_K_M | 45.41 | 3.4451 | 0.40% |
Q6_K | 52.70 | 3.4367 | 0.16% |
fp16 | 128.5 | 3.4313 | - |