diff options
author | Georgi Gerganov <ggerganov@gmail.com> | 2023-05-12 00:23:08 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-05-12 00:23:08 +0300 |
commit | b9fd7eee57df101d4a3e3eabc9fd6c2cb13c9ca1 (patch) | |
tree | bbc617734354146eeffed3ba58cd1b4cfebb4aa6 /ggml.h | |
parent | b608b55a3ea8e4760c617418538465449175bdb8 (diff) |
ggml : remove bit shuffling (#1405)
* ggml : remove Q4_0 bit shufling (ARM NEON)
* ggml : remove Q4_1 bit shuffling (ARM NEON + reference)
* ggml : nibbles_from_floats() + bytes_from_nibbles() (ARM NEON)
* ggml : remove Q4_2 bit shuffling (WIP, BROKEN)
* ggml : remove Q5_0 bit shuffling (ARM NEON)
* ggml : 2x faster scalar implementations
* ggml : remove Q5_1 bit shuffling (ARM NEON + scalar)
* ggml : simplify scalar dot
* ggml : remove WASM SIMD bit shuffling + remove vzip for ARM 32-bit
* ggml : fix Q4_1 quantization
* ggml : update cuBLAS + normalize variable names
* ggml : remove Q4_2 mode
* ggml : minor formatting
* ggml : fix Q5_0 quantization
* scripts : add script for measuring the time per token
* AVX implementations (#1370)
* ggml : uniform 5th bit extraction
* llama : produce error upon loading old model files
* llama : fix model magic/version write
* ggml : speed-up Q5_0 + Q5_1 at 4 threads
* ggml : preserve old Q4 and Q5 formats
* ggml : simplify Q8_1 - no need for low / high sums anymore
* ggml : fix Q8_0 and Q8_1 rounding
* Revert "AVX implementations (#1370)"
This reverts commit 948d124837f9d287d8490f41338e0e4cceb0814f.
* ggml : fix AVX2 implementation
* sha : update hashes for 7B and 13B
* readme : update timings + remove warning banner
* llama : update v2 PR number to 1405
* ggml : fix WASM comments
* ggml : back to original bit order
* readme : add note that Q4 and Q5 have been changed
* llama : fix return for unknown version
---------
Co-authored-by: Stephan Walter <stephan@walter.name>
Diffstat (limited to 'ggml.h')
-rw-r--r-- | ggml.h | 4 |
1 files changed, 1 insertions, 3 deletions
@@ -231,7 +231,7 @@ extern "C" { GGML_TYPE_F16 = 1, GGML_TYPE_Q4_0 = 2, GGML_TYPE_Q4_1 = 3, - GGML_TYPE_Q4_2 = 4, + // GGML_TYPE_Q4_2 = 4, support has been removed // GGML_TYPE_Q4_3 (5) support has been removed GGML_TYPE_Q5_0 = 6, GGML_TYPE_Q5_1 = 7, @@ -251,7 +251,6 @@ extern "C" { GGML_FTYPE_MOSTLY_Q4_0 = 2, // except 1d tensors GGML_FTYPE_MOSTLY_Q4_1 = 3, // except 1d tensors GGML_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16 - GGML_FTYPE_MOSTLY_Q4_2 = 5, // except 1d tensors GGML_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors GGML_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors GGML_FTYPE_MOSTLY_Q5_1 = 9, // except 1d tensors @@ -876,7 +875,6 @@ extern "C" { GGML_API size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist); - GGML_API size_t ggml_quantize_q4_2(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist); GGML_API size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist); |