b2128 #83
Merged
b2128 #83
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* server: add mistral chat template * server: fix typo * server: rename template mistral to llama2 * server: format_llama2: remove BOS * server: validate "--chat-template" argument * server: clean up using_chatml variable Co-authored-by: Jared Van Bortel <[email protected]> --------- Co-authored-by: Jared Van Bortel <[email protected]>
* ggml: aarch64: implement smmla kernel for q8_0_q8_0 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q8_0_q8_0 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: aarch64: implement smmla kernel for q4_0_q8_0 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q4_0_q8_0 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: aarch64: implement smmla kernel for q4_1_q8_1 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q4_1_q8_1 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: update unit tests for the new vec_dot interface * llama.cpp: add MATMUL_INT8 capability to system_info
* server: allow to specify tokens as strings in logit_bias * Apply suggestions from code review Co-authored-by: Georgi Gerganov <[email protected]> --------- Co-authored-by: Georgi Gerganov <[email protected]>
* common: use enums for sampler types * Apply suggestions from code review Co-authored-by: Georgi Gerganov <[email protected]> * minor : spaces --------- Co-authored-by: Georgi Gerganov <[email protected]>
* vulkan: refactor guess_matmul_pipeline for vendor Refactor ggml_vk_guess_matmul_pipeline to simplify adding per-vendor conditionals. Signed-off-by: Sergio Lopez <[email protected]> * vulkan: only use M-sized matmul on Apple GPUs L-sized and S-sized matmuls are broken on Apple GPUs, force using M-size with this vendor. Signed-off-by: Sergio Lopez <[email protected]> --------- Signed-off-by: Sergio Lopez <[email protected]>
Flake lock file updates:
• Updated input 'nixpkgs':
'github:NixOS/nixpkgs/b8b232ae7b8b144397fdb12d20f592e5e7c1a64d' (2024-01-31)
→ 'github:NixOS/nixpkgs/f8e2ebd66d097614d51a56a755450d4ae1632df1' (2024-02-07)
* BERT model graph construction (build_bert) * WordPiece tokenizer (llm_tokenize_wpm) * Add flag for non-causal attention models * Allow for models that only output embeddings * Support conversion of BERT models to GGUF * Based on prior work by @xyzhang626 and @skeskinen --------- Co-authored-by: Jared Van Bortel <[email protected]> Co-authored-by: Jared Van Bortel <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
* CUDA: mul_mat_vec_q tiling, refactor mul mat logic Co-authored-by: slaren <[email protected]> --------- Co-authored-by: slaren <[email protected]>
Nexesenex
pushed a commit
that referenced
this pull request
Dec 22, 2024
* iq4_k_xxs: basics * WIP + adding iq3_kl quantization mix * iq4_xxs: this looks very viable compared to iq4_xs At the same 4.25 bpw PPL is always better, for some models significantly better. I'll rename to iq4_ks and keep it. * iq4_xxs: CUDA dot product We get TG-128 = 126 t/s for LLaMA-3.1-8B, compared to 123 t/s for q4_0. * iq4_xxs: scalar CPU dot product Also fix the breakage I caused with the dedicated work buffer quantization portion when the multiplication is not done via iqk_mul_mat. * iq4_xxs: Zen4 I noticed that iq4_xs is wrong on Zen4 (and possibly AVX2). Again the same mistake of packing int32_t back to int16_t, which overflows occasionally (just occasionally, that's why the result doesn't look completely wrong, so I didn't notice). * Fix iq4_xs (Zen4) * iq4_xxs: AVX2 * iq4_xxs: ARM_NEON * iq4_xxs: Metal * iq4_xxs: slightly faster TG on Metal * iq4_xxs: rename to iq4_ks After all, tt is a smaller variant of iq4_k. * iq3_kl: use iq4_ks instead of iq4_k/iq4_xs --------- Co-authored-by: Iwan Kawrakow <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.