sync : llama.cpp #773

* gguf : add support for I64 and F64 arrays GGML currently does not support I64 or F64 arrays and they are not often used in machine learning, however if in the future the need arises, it would be nice to add them now, so that the types are next to the other types I8, I16, I32 in the enums, and it also reserves their type number. Furthermore, with this addition the GGUF format becomes very usable for most computational applications of NumPy (being compatible with the most common NumPy dtypes: i8, i16, i32, i64, f32, f64), providing a faster, and more versatile alternative to the `npz` format, and a simpler alternative to the `hdf5` format. The change in this PR seems small, not significantly increasing the maintenance burden. I tested this from Python using GGUFWriter/Reader and `gguf-dump`, as well as from C, everything seems to work. * Fix compiler warnings

* Fix non-intel device selection * Update ggml-sycl.cpp Co-authored-by: Neo Zhang Jianyu <[email protected]> * Update ggml-sycl.cpp Co-authored-by: Neo Zhang Jianyu <[email protected]> --------- Co-authored-by: Abhilash Majumder <[email protected]> Co-authored-by: Neo Zhang Jianyu <[email protected]>

Co-authored-by: GainLee <[email protected]>

* backend : offload large batches to GPU * fix hip * code cleanup * fix CUDA split buffers * Update ggml-backend-impl.h Co-authored-by: Johannes Gäßler <[email protected]> * cuda : fix memset without set_device * imatrix : remove sched affix from weight names * sched : add a new split if the current one has too many inputs reduce max inputs per split more cleanup * update backends ggml-ci --------- Co-authored-by: Johannes Gäßler <[email protected]>

* cuda : refactor to remove global resources

…/6185)

…a/6183) * k_cache: be able to use Q5_0 * k_cache: be able to use Q5_1 on CODA * k_cache: be able to use Q5_0 on Metal * k_cache: be able to use Q5_1 on Metal * k_cache: be able to use IQ4_NL - just CUDA for now * k_cache: be able to use IQ4_NL on Metal * k_cache: add newly added supported types to llama-bench and CUDA supports_op --------- Co-authored-by: Iwan Kawrakow <[email protected]>

* Make quantize_row_iq4_nl do the same thing is quantization on CUDA * Make quantize_row_iq4_nl do the same thing is quantization on CUDA This time for real. backend-ops tests pass. * Now fix test-quantize-fns --------- Co-authored-by: Iwan Kawrakow <[email protected]>

* metal : require ne00 >= 128 for mat-mat kernels ggml-ci * llama : pad n_ctx by 32 ggml-ci

* metal : proper assert for mat-mat memory alignment ggml-ci * readme : add notice about the bug fix * metal : fix the fix ggml-ci

… (llama/6208) * cuda : add LLAMA_CUDA_NO_PEER_COPY to workaround broken ROCm p2p copy * add LLAMA_CUDA_NO_PEER_COPY to HIP build

also fix missing #defines before windows.h, and BPE LF token on MSVC

* remove no USM methods * leave the schedule to ggml_backend_sched entirely

…6272) * would throw error on VS2022 on GGML_FREE(wmode) * wchar_t is usually 2 bytes, but malloc wants bytes * therefore `*wmode_p++ = (wchar_t)*mode;` could write off the end of the allocation * Fixes error possibly introduced by ggerganov/llama.cpp#6248

This change causes some quants (e.g. Q4_0, Q8_0) to go faster on some architectures (e.g. AMD Zen 4).

Co-authored-by: Iwan Kawrakow <[email protected]>

* iq1_m: basics * iq1_m: basics-2 * iq1_m: CUDA dequantize works Very 1st shot I get PPL = 9.76 for LLaMA-v2-7B. * iq1_m: separate shifts for each group of 8 in a block We get PPL(LLaMA-v2-7B ) = 9.2810 PPL(LLaMA-v2-13B) = 6.8105 Not bad, but slightly higher than sqrt(PPL(IQ1_S) * PPL(IQ2_XXS)) which is the expected outcome given that IQ1_M is halfway between IQ1_S and IQ2_XXS in terms of bpw. From this, we would expect PPL = 9.14 for LLaMA-v2-7B PPL = 6.63 for LLaMA-v2-13B * iq1_m: go to 3-bit scales There is slight increase in PPL, but the 0.0625 bpw reduction in size is totally worth it. We now have PPL(LLaMA-v2-7B ) = 9.4469 at 1.96 bpw PPL(LLaMA-v2-13B) = 6.8717 at 1.93 bpw PPL(LLaMA-v2-70B) = 4.8568 at 1.85 bpw * iq1_m: scalar dot product * iq1_m: AVX2 dot product * iq1_m: very slightly faster AVX2 dot product * iq1_m: ARM_NEON dot product Works, but very slow (10.5 t/s) * iq1_m: Metal - dequantize works, dot product does not * iq1_m: Metal now works About the same performance as iq1_s. * iq1_m: minor * iq1_m: checking pure iq1_m quantization It is pretty bad: PPL(LLaMA-v2-7B) = 34 if we quantize output.weight with Q4_K. * iiq1_m: slightly faster ARM_NEON dot product 10.5 t/s -> 11.65 t/s * iq1_m: faster ARM_NEON dot product 11.65 t/s -> 14.9 t/s * iq1_m: another minor ARM_NEON dot product improvement 14.9 -> 15.0 t/s * iq1_m: small PPL improvement via super-block scale adjustment After quantizing block scales redo the super-block scale fit. PPL(LLaMA-v2-7B ) = 9.3346 PPL(LLaMA-v2-13B) = 6.8419 PPL(LLaMA-v2-70B) = 4.8294 PPL(Mistral-7B ) = 8.1624 * iq1_m: adapt to CUDA refactoring * iq1_m: remove unused variable We have progressed to warnings being errors. * iq1_m: add to backend-ops tests * iq1_m: fix Windows ARM * iq1_m: use common definition of iq1m_scale_t * cuda: assert -> NO_DEVICE_CODE * iq1_M: PR comments --------- Co-authored-by: Iwan Kawrakow <[email protected]>

* llama : greatly reduce logits memory usage * llama : more compact state saving and reloading * llama : fix lctx.n_outputs not being set before building graph * perplexity : adapt to the logits API changes * perplexity : fix Winogrande, use correct logits for second choice start The first logits used to evaluate the second choice were not from the end of the common prefix; instead, they were the logits from the end of the first choice. This has been corrected. The previous implementation sometimes had outliers in the scores of choices for some tasks, and the logic to skip choices words in the log-likelihood evaluation probably was an attempt to reduce those, but it was complex and didn't quite seem to be the right thing. This is simpler now, and the outlier scores aren't there anymore. * perplexity : normalize spaces and punctuation in Winogrande sentences * llama : fix embedding conditions * llama : fix llama_get_embeddings_ith when the resulting id is 0 * llama : fix wrong n_outputs in llama_set_inputs A mismatch happened when using a smaller n_ubatch than n_batch and then using llama_batch_get_one(). The decision of what n_outputs should be now almost fully depends on how lctx.n_outputs is set in llama_decode_internal. The conditions are simpler this way. * llama : when saving the state, recalculate n_outputs This ensures the correct number of outputs for the entire previous batch is stored in the session file, even when n_ubatch is smaller than n_batch. * llama : fix not-skipping outputs of non-causal models * llama : fix running a batch with n_outputs == 0 It previously worked because lctx.inp_out_ids was not initialized, so it pointed to some garbage address which was somehow still valid when I ran my tests. * llama : keep same graph topology even when n_outputs == 0 * ggml : saner ggml_can_repeat with empty tensors * ggml : future-proof ggml_is_empty by using GGML_MAX_DIMS - 1 * ggml : do not multi-thread ops returning empty tensors * ggml : make ggml_is_empty public and work with views * llama : use a vector for ctx->output_ids * llama : rework reallocation logic for llama_output_reserve Now comparing the actual size with the new total size of the output buffer to allow more efficient enabling and disabling of the embeddings and/or logits output in the future. * ggml : skip empty tensors in all backends * llama : fix llama_output_reserve nullptr deref when new_size is 0 * perplexity : make Winogrande work as it does on master The problems with the Winogrande implementation will need to be fixed in a separate PR to ease review. * llama : clearer error messages for invalid logits or embeddings ids * llama : assert all models that can have inp_out_ids Since the graph topology is now constant, this presence check can be done even when there are no outputs. * llama : assert logits and embd buffers exist before writing to them * llama : handle errors from llama_output_reserve at call sites * perplexity : make hellaswag and multiple-choice outputs identical to master Due to how the KV cache is updated, the logprobs for tokens in a batch are very slightly affected by the other tokens present in the batch, so to make hellaswag and multiple-choice return exactly the same results as on master, the last token of each sequence needs to be evaluated even though its output is not used at all. This will probably be changed back in the future to make these benchmarks a tiny bit faster. * perplexity : fix division by zero when using less than 100 multiple-choice tasks * llama : allow loading state saved with a different ctx size When loading a session file, the context size is now only required to be at least enough to load the KV cells contained in that session file, instead of requiring to use exactly the same context size as when saving. Doing this enables the use-case of extending or shrinking the context size of a saved session. This breaks existing session files because the meaning of kv_buf_size is slightly changed (previously it was the size of the whole KV cache, now it's only the size of the saved part of it). This allows for finer-grained sanity checks when loading in an effort to keep kv_buf_size useful even when the kv_size is changed. * llama : minor ggml-ci * readme : update recent API changes, and warn about Vulkan --------- Co-authored-by: Georgi Gerganov <[email protected]>

* iq1_m: make it work for QK_K = 64 (WIP) * iq1_m: make it work for QK_K = 64 (scalar and AVX2) * iq1_m: QK_K = 64 seems to work on Metal and ARM_NEON --------- Co-authored-by: Iwan Kawrakow <[email protected]>

* Fix batched impl * Maintain previous behaviour for igpu * retrigger CI --------- Co-authored-by: Abhilash Majumder <[email protected]>

ggml-ci

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

sync : llama.cpp #773

sync : llama.cpp #773

Commits on Mar 27, 2024